Total relevant papers: 76
Paper selection prompt and criteria at the bottom
Table of contents with paper titles:
Robix: A Unified Model for Robot Interaction, Reasoning and Planning Authors: Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li
OmniReason: A Temporal-Guided Vision-Language-Action Framework for Autonomous Driving Authors: Pei Liu, Qingtian Ning, Xinyan Lu, Haipeng Liu, Weiliang Ma, Dangen She, Peng Jia, Xianpeng Lang, Jun Ma
OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination Authors: Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu, Chao Sun, Rongzhou Zhang, Guanyu Zhou, Lijie Wen, Xuming Hu
Kwai Keye-VL 1.5 Technical Report Authors: Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang
Multimodal Iterative RAG for Knowledge Visual Question Answering Authors: Changin Choi, Wonseok Lee, Jungmin Ko, Wonjong Rhee
OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning Authors: Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, Cihang Xie
ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association Authors: Ganlin Zhang, Shenhan Qian, Xi Wang, Daniel Cremers
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use Authors: Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen
Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs Authors: Guangzong Si, Hao Yin, Xianfei Li, Qing Ding, Wenlong Liao, Tao He, Pai Peng
RS-OOD: A Vision-Language Augmented Framework for Out-of-Distribution Detection in Remote Sensing Authors: Yingrui Ji, Jiansheng Chen, Jingbo Chen, Anzhi Yue, Chenhao Wang, Kai Li, Yao Zhu
HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization Authors: Joohyun Chang, Soyeon Hong, Hyogun Lee, Seong Jong Ha, Dongho Lee, Seong Tae Kim, Jinwoo Choi
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning Authors: Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Bo Li, Chen Dun, Chong Liu, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, Guang Shi
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation Authors: Jiahao Li Yang Lu, Yachao Zhang, Fangyong Wang, Yuan Xie, Yanyun Qu
Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models Authors: Sihao Wu, Gaojie Jin, Wei Huang, Jianhong Wang, Xiaowei Huang
Improving Large Vision and Language Models by Learning from a Panel of Peers Authors: Jefferson Hernandez, Jing Shi, Simon Jenni, Vicente Ordonez, Kushal Kafle
Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery Authors: Xinrui Gong, Oliver Hahn, Christoph Reich, Krishnakant Singh, Simone Schaub-Meyer, Daniel Cremers, Stefan Roth
Unified Supervision For Vision-Language Modeling in 3D Computed Tomography Authors: Hao-Chih Lee, Zelong Liu, Hamza Ahmed, Spencer Kim, Sean Huver, Vishwesh Nath, Zahi A. Fayad, Timothy Deyer, Xueyan Mei
Draw-In-Mind: Learning Precise Image Editing via Chain-of-Thought Imagination Authors: Ziyun Zeng, Junhao Zhang, Wei Li, Mike Zheng Shou
DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion Authors: Junxiang Liu, Junming Lin, Jiangtong Li, Jie Li
Language and Experience: A Computational Model of Social Learning in Complex Tasks Authors: C'edric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman, Jacob Andreas, Joshua Tenenbaum
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors Authors: Xiangchen Wang, Jinrui Zhang, Teng Wang, Haigang Zhang, Feng Zheng
Neural Scene Designer: Self-Styled Semantic Image Manipulation Authors: Jianman Lin, Tianshui Chen, Chunmei Qing, Zhijing Yang, Shuangping Huang, Yuheng Ren, Liang Lin
AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent Authors: Jingru Fan, Yufan Dang, Jingyao Wu, Huatao Li, Runde Yang, Xiyuan Yang, Yuheng Wang, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Dahai Li, Chen Qian
LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Authors: Lianyu Hu, Fanhua Shang, Wei Feng, Liang Wan
ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation Authors: Weilong Yan, Xin Zhang, Robby T. Tan
Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning Authors: Long Zhang, Peipei Song, Jianfeng Dong, Kun Li, Xun Yang
Guided Model-based LiDAR Super-Resolution for Resource-Efficient Automotive scene Segmentation Authors: Alexandros Gkillas, Nikos Piperigkos, Aris S. Lalos
CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation Authors: Zixin Zhu, Kevin Duarte, Mamshad Nayeem Rizve, Chengyuan Xu, Ratheesh Kalarot, Junsong Yuan
Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives Authors: Nikolaos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey Authors: Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai
Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders Authors: Faizan Farooq Khan, Vladan Stojni'c, Zakaria Laskar, Mohamed Elhoseiny, Giorgos Tolias
DGL-RSIS: Decoupling Global Spatial Context and Local Class Semantics for Training-Free Remote Sensing Image Segmentation Authors: Boyi Li, Ce Zhang, Richard M. Timmerman, Wenxuan Bao
Conformal Predictive Monitoring for Multi-Modal Scenarios Authors: Francesca Cairoli, Luca Bortolussi, Jyotirmoy V. Deshmukh, Lars Lindemann, Nicola Paoletti
C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Object Detection Authors: Abdellah Zakaria Sellam, Ilyes Benaissa, Salah Eddine Bekhouche, Abdenour Hadid, Vito Ren'o, Cosimo Distante
ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization Authors: Thinh-Phuc Nguyen, Thanh-Hai Nguyen, Gia-Huy Dinh, Lam-Huy Nguyen, Minh-Triet Tran, Trung-Nghia Le
EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions Authors: Dinh-Khoi Vo, Van-Loc Nguyen, Minh-Triet Tran, Trung-Nghia Le
Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing Authors: Quan Dao, Xiaoxiao He, Ligong Han, Ngan Hoai Nguyen, Amin Heyrani Nobar, Faez Ahmed, Han Zhang, Viet Anh Nguyen, Dimitris Metaxas
Variation-aware Vision Token Dropping for Faster Large Vision-Language Models Authors: Junjie Chen, Xuyang Liu, Zichen Wen, Yiyu Wang, Siteng Huang, Honggang Chen
Automated Wildfire Damage Assessment from Multi view Ground level Imagery Via Vision Language Models Authors: Miguel Esparza, Archit Gupta, Ali Mostafavi, Kai Yin, Yiming Xiao
Spotlighter: Revisiting Prompt Tuning from a Representative Mining View Authors: Yutong Gao, Maoyuan Shao, Xinyang Huang, Chuang Zhu, Lijuan Sun, Yu Weng, Xuan Liu, Guoshun Nan
Enabling Federated Object Detection for Connected Autonomous Vehicles: A Deployment-Oriented Evaluation Authors: Komala Subramanyam Cherukuri, Kewei Sha, Zhenhua Huang
Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs Authors: Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci, Zhe Han, Yunpeng Zhang
LLM-empowered Agents Simulation Framework for Scenario Generation in Service Ecosystem Governance Authors: Deyu Zhou, Yuqi Hou, Xiao Xue, Xudong Lu, Qingzhong Li, Lizhen Cui
Social World Models Authors: Xuhui Zhou, Jiarui Liu, Akhila Yerukola, Hyunwoo Kim, Maarten Sap
Towards Open-World Retrieval-Augmented Generation on Knowledge Graph: A Multi-Agent Collaboration Framework Authors: Jiasheng Xu, Mingda Li, Yongqiang Tang, Peijie Wang, Wensheng Zhang
Dynamic Speculative Agent Planning Authors: Yilin Guan, Wenyue Hua, Qingfeng Lan, Sun Fei, Dujian Ding, Devang Acharya, Chi Wang, William Yang Wang
Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework Authors: Wei Lu, Lingyu Zhu, Si-Bao Chen
Beyond Memorization: Reasoning-Driven Synthesis as a Mitigation Strategy Against Benchmark Contamination Authors: Terry Jingchen Zhang, Gopal Dev, Ning Wang, Nicole Ni, Wenyuan Jiang, Yinya Huang, Bernhard Sch"olkopf, Mrinmaya Sachan, Zhijing Jin
Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars Authors: Vanessa Sklyarova, Egor Zakharov, Malte Prinzler, Giorgio Becherini, Michael J. Black, Justus Thies
Causal Interpretation of Sparse Autoencoder Features in Vision Authors: Sangyu Han, Yearim Kim, Nojun Kwak
Unsupervised Training of Vision Transformers with Synthetic Negatives Authors: Nikolaos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki
Counterfactual Sensitivity for Faithful Reasoning in Language Models Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Diffusion-Based Image-to-Brain Signal Generation with Cross-Attention Mechanisms for Visual Prostheses Authors: Ganxi Xu, Jinyi Long, Jia Zhang
Iterative Low-rank Network for Hyperspectral Image Denoising Authors: Jin Ye, Fengchao Xiong, Jun Zhou, Yuntao Qian
Pose as Clinical Prior: Learning Dual Representations for Scoliosis Screening Authors: Zirui Zhou, Zizhao Peng, Dongyang Jin, Chao Fan, Fengwei An, Shiqi Yu
DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining Authors: Yihong Wu, Jinqiao Wei, Xionghui Zhao, Yidi Li, Shaoyi Du, Bin Ren, Nicu Sebe
An LLM-enabled semantic-centric framework to consume privacy policies Authors: Rui Zhao, Vladyslav Melnychuk, Jun Zhao, Jesse Wright, Nigel Shadbolt
DroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective Authors: Zhipeng Weng, Xiaopeng Liu, Ce Liu, Xingyuan Guo, Yukai Shi, Liang Lin
Throttling Web Agents Using Reasoning Gates Authors: Abhinav Kumar, Jaechul Roh, Ali Naseh, Amir Houmansadr, Eugene Bagdasarian
Performance is not All You Need: Sustainability Considerations for Algorithms Authors: Xiang Li, Chong Zhang, Hongpeng Wang, Shreyank Narayana Gowda, Yushi Li, Xiaobo Jin
RibPull: Implicit Occupancy Fields and Medial Axis Extraction for CT Ribcage Scans Authors: Emmanouil Nikolakakis, Amine Ouasfi, Julie Digne, Razvan Marinescu
Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective Authors: Jiacheng Jiang, Yuan Meng, Chen Tang, Han Yu, Qun Li, Zhi Wang, Wenwu Zhu
Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis Authors: Mengke Li, Lihao Chen, Peng Zhang, Yiu-ming Cheung, Hui Huang
Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimation Authors: Lee Chae-Yeon, Nam Hyeon-Woo, Tae-Hyun Oh
Ultra Strong Machine Learning: Teaching Humans Active Learning Strategies via Automated AI Explanations Authors: Lun Ai, Johannes Langer, Ute Schmid, Stephen Muggleton
NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models Authors: Shumpei Takezaki, Ryoma Bise, Shinnosuke Matsuo
Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation Authors: Xuechao Zou, Shun Zhang, Xing Fu, Yue Li, Kai Li, Yushe Cao, Congyan Lang, Pin Tao, Junliang Xing
From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentation Authors: Tao Wang, Zhenxuan Zhang, Yuanbo Zhou, Xinlin Zhang, Yuanbin Chen, Tao Tan, Guang Yang, Tong Tong
Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation Authors: Fuyou Mao, Beining Wu, Yanfeng Jiang, Han Xue, Yan Tang, Hao Zhang
The Need for Verification in AI-Driven Scientific Discovery Authors: Cristina Cornelio, Takuya Ito, Ryan Cory-Wright, Sanjeeb Dash, Lior Horesh
Multi-Agent Data Visualization and Narrative Generation Authors: Anton Wolter, Georgios Vidalakis, Michael Yu, Ankit Grover, Vaishali Dhanoa
Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains Authors: Yumeng Lin, Dong Li, Xintao Wu, Minglai Shao, Xujiang Zhao, Zhong Chen, Chen Zhao
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First Authors: Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito, Shuo Yuan, Ion Stoica, Matei Zaharia, Alvin Cheung, Natacha Crooks, Joseph E. Gonzalez, Aditya G. Parameswaran
Secure and Scalable Face Retrieval via Cancelable Product Quantization Authors: Haomiao Tang, Wenjie Li, Yixiang Qiu, Genping Wang, Shu-Tao Xia
RiverScope: High-Resolution River Masking Dataset Authors: Rangel Daroya, Taylor Rowley, Jonathan Flores, Elisa Friedmann, Fiona Bennitt, Heejin An, Travis Simmons, Marissa Jean Hughes, Camryn L Kluetmeier, Solomon Kica, J. Daniel V'elez, Sarah E. Esenther, Thomas E. Howard, Yanqi Ye, Audrey Turcotte, Colin Gleason, Subhransu Maji
MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure Authors: Xiufeng Huang, Ziyuan Luo, Qi Song, Ruofei Wang, Renjie Wan
ArXiv ID: 2509.01106 Authors: Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li
Abstract: We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.
Comment: Matches criteria 1 and 3 as it introduces a unified model for robot reasoning, task planning, and natural language interaction, with a focus on spatial reasoning and embodied agents. Relevance: 10 Novelty: 8
ArXiv ID: 2509.00789 Authors: Pei Liu, Qingtian Ning, Xinyan Lu, Haipeng Liu, Weiliang Ma, Dangen She, Peng Jia, Xianpeng Lang, Jun Ma
Abstract: Recent advances in vision-language models (VLMs) have demonstrated impressive spatial reasoning capabilities for autonomous driving, yet existing methods predominantly focus on static scene understanding while neglecting the essential temporal dimension of real-world driving scenarios. To address this critical limitation, we propose the OmniReason framework, which establishes robust spatiotemporal reasoning by jointly modeling dynamic 3D environments and their underlying decision-making processes. Our work makes two fundamental advances: (1) We introduce OmniReason-Data, two large-scale vision-language-action (VLA) datasets with dense spatiotemporal annotations and natural language explanations, generated through a novel hallucination-mitigated auto-labeling pipeline that ensures both physical plausibility and temporal coherence; (2) We develop the OmniReason-Agent architecture, which integrates a sparse temporal memory module for persistent scene context modeling and an explanation generator that produces human-interpretable decision rationales, facilitated by our spatiotemporal knowledge distillation approach that effectively captures spatiotemporal causal reasoning patterns. Comprehensive experiments demonstrate state-of-the-art performance, where OmniReason-Agent achieves significant improvements in both open-loop planning tasks and visual question answering (VQA) benchmarks, while establishing new capabilities for interpretable, temporally-aware autonomous vehicles operating in complex, dynamic environments.
Comment: Matches criteria 1 and 3 as it focuses on spatiotemporal reasoning for embodied agents in autonomous driving, introducing new datasets and methods. Relevance: 10 Novelty: 8
ArXiv ID: 2509.00723 Authors: Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu, Chao Sun, Rongzhou Zhang, Guanyu Zhou, Lijie Wen, Xuming Hu
Abstract: Recently, Omni-modal large language models (OLLMs) have sparked a new wave of research, achieving impressive results in tasks such as audio-video understanding and real-time environment perception. However, hallucination issues still persist. Similar to the bimodal setting, the priors from the text modality tend to dominate, leading OLLMs to rely more heavily on textual cues while neglecting visual and audio information. In addition, fully multimodal scenarios introduce new challenges. Most existing models align visual or auditory modalities with text independently during training, while ignoring the intrinsic correlations between video and its corresponding audio. This oversight results in hallucinations when reasoning requires interpreting hidden audio cues embedded in video content. To address these challenges, we propose OmniDPO, a preference-alignment framework designed to mitigate hallucinations in OLLMs. Specifically, OmniDPO incorporates two strategies: (1) constructing text-preference sample pairs to enhance the model's understanding of audio-video interactions; and (2) constructing multimodal-preference sample pairs to strengthen the model's attention to visual and auditory information. By tackling both challenges, OmniDPO effectively improves multimodal grounding and reduces hallucination. Experiments conducted on two OLLMs demonstrate that OmniDPO not only effectively mitigates multimodal hallucinations but also significantly enhances the models' reasoning capabilities across modalities. All code and datasets will be released upon paper acceptance.
Comment: Matches criteria 2 and 5 as it addresses multimodal hallucination in Omni-modal large language models, focusing on audio-video-text integration and reasoning. Relevance: 9 Novelty: 8
ArXiv ID: 2509.01563 Authors: Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang
Abstract: In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a challenging area due to the dynamic and information-dense nature of videos. Existing models struggle with the trade-off between spatial resolution and temporal coverage when processing video content. We present Keye-VL-1.5, which addresses fundamental challenges in video comprehension through three key innovations. First, we introduce a novel Slow-Fast video encoding strategy that dynamically allocates computational resources based on inter-frame similarity, processing key frames with significant visual changes at higher resolution (Slow pathway) while handling relatively static frames with increased temporal coverage at lower resolution (Fast pathway). Second, we implement a progressive four-stage pre-training methodology that systematically extends the model's context length from 8K to 128K tokens, enabling processing of longer videos and more complex visual content. Third, we develop a comprehensive post-training pipeline focusing on reasoning enhancement and human preference alignment, incorporating a 5-step chain-of-thought data construction process, iterative GSPO-based reinforcement learning with progressive prompt hinting for difficult cases, and alignment training. Through extensive evaluation on public benchmarks and rigorous internal human assessment, Keye-VL-1.5 demonstrates significant improvements over existing models, particularly excelling in video understanding tasks while maintaining competitive performance on general multimodal benchmarks.
Comment: Matches criterion 2 (Visual and Multimodal Large Language Models) and criterion 6 (Video Understanding) as it introduces a novel video encoding strategy and training methodology for video understanding in multimodal large language models. Relevance: 9 Novelty: 8
ArXiv ID: 2509.00798 Authors: Changin Choi, Wonseok Lee, Jungmin Ko, Wonjong Rhee
Abstract: While Multimodal Large Language Models (MLLMs) have significantly advanced multimodal understanding, their performance remains limited on knowledge-intensive visual questions that require external knowledge beyond the image. Retrieval-Augmented Generation (RAG) has become a promising solution for providing models with external knowledge, its conventional single-pass framework often fails to gather sufficient knowledge. To overcome this limitation, we propose MI-RAG, a Multimodal Iterative RAG framework that leverages reasoning to enhance retrieval and update reasoning over newly retrieved knowledge across modalities. At each iteration, MI-RAG leverages an accumulated reasoning record to dynamically formulate a multi-query. These queries then drive a joint search across heterogeneous knowledge bases containing both visually-grounded and textual knowledge. The newly acquired knowledge is synthesized into the reasoning record, progressively refining understanding across iterations. Experiments on challenging benchmarks, including Encyclopedic VQA, InfoSeek, and OK-VQA, show that MI-RAG significantly improves both retrieval recall and answer accuracy, establishing a scalable approach for compositional reasoning in knowledge-intensive VQA.
Comment: Matches criteria 2 and 6 as it focuses on multimodal large language models and their application to knowledge-intensive visual question answering. Relevance: 9 Novelty: 8
ArXiv ID: 2509.01644 Authors: Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, Cihang Xie
Abstract: This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set of multimodal benchmarks while substantially cutting both training time and memory consumption. For example, with ViT-L/14, it reduces training time by about 1.5x (from 83h to 57h), and memory usage by about 1.8x (from 24.5GB to 13.8GB, equivalently allowing the maximum batch size to grow from 2k to 8k). This superior training efficiency also allows us to scale far beyond the largest vision encoder used in OpenVision, reaching more than 1 billion parameters. We hold a strong belief that this lightweight, generative-only paradigm is compelling for future vision encoder development in multimodal foundation models.
Comment: Matches criteria 2 and 5 as it introduces a simplified generative framework for multimodal learning with vision-language models. Relevance: 9 Novelty: 7
ArXiv ID: 2509.01584 Authors: Ganlin Zhang, Shenhan Qian, Xi Wang, Daniel Cremers
Abstract: We present ViSTA-SLAM as a real-time monocular visual SLAM system that operates without requiring camera intrinsics, making it broadly applicable across diverse camera setups. At its core, the system employs a lightweight symmetric two-view association (STA) model as the frontend, which simultaneously estimates relative camera poses and regresses local pointmaps from only two RGB images. This design reduces model complexity significantly, the size of our frontend is only 35% that of comparable state-of-the-art methods, while enhancing the quality of two-view constraints used in the pipeline. In the backend, we construct a specially designed Sim(3) pose graph that incorporates loop closures to address accumulated drift. Extensive experiments demonstrate that our approach achieves superior performance in both camera tracking and dense 3D reconstruction quality compared to current methods. Github repository: https://github.com/zhangganlin/vista-slam
Comment: Matches criteria 1 and 3 as it introduces a novel visual SLAM system with improvements in spatial reasoning and camera tracking. Relevance: 9 Novelty: 7
ArXiv ID: 2509.01055 Authors: Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated success in enhancing LLM reasoning capabilities, but remains limited to single-turn interactions without tool integration. While recent Agentic Reinforcement Learning with Tool use (ARLT) approaches have emerged to address multi-turn tool interactions, existing works develop task-specific codebases that suffer from fragmentation, synchronous execution bottlenecks, and limited extensibility across domains. These inefficiencies hinder broader community adoption and algorithmic innovation. We introduce VerlTool, a unified and modular framework that addresses these limitations through systematic design principles. VerlTool provides four key contributions: (1) upstream alignment with VeRL ensuring compatibility and simplified maintenance, (2) unified tool management via standardized APIs supporting diverse modalities including code execution, search, SQL databases, and vision processing, (3) asynchronous rollout execution achieving near 2$\times$ speedup by eliminating synchronization bottlenecks, and (4) comprehensive evaluation demonstrating competitive performance across 6 ARLT domains. Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms. We train and evaluate models on mathematical reasoning, knowledge QA, SQL generation, visual reasoning, web search, and software engineering tasks, achieving results comparable to specialized systems while providing unified training infrastructure. The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions, significantly reducing development overhead and providing a scalable foundation for tool-augmented RL research. Our code is open-sourced at https://github.com/TIGER-AI-Lab/verl-tool.
Comment: Matches criterion 3 (Embodied/Robotic AI: New Benchmarks or Methods) as it introduces a modular framework for agentic reinforcement learning with tool use. Relevance: 9 Novelty: 7
ArXiv ID: 2509.00371 Authors: Guangzong Si, Hao Yin, Xianfei Li, Qing Ding, Wenlong Liao, Tao He, Pai Peng
Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive advances, yet object hallucination remains a persistent challenge. Existing methods, based on the flawed assumption that omission and fabrication hallucinations share a common cause, often reduce omissions only to trigger more fabrications. In this work, we overturn this view by demonstrating that omission hallucinations arise from insufficient confidence when mapping perceived visual features to linguistic expressions, whereas fabrication hallucinations result from spurious associations within the cross-modal representation space due to statistical biases in the training corpus. Building on findings from visual attention intervention experiments, we propose the Visual-Semantic Attention Potential Field, a conceptual framework that reveals how the model constructs visual evidence to infer the presence or absence of objects. Leveraging this insight, we introduce Visual Potential Field Calibration (VPFC), a plug-and-play hallucination mitigation method that effectively reduces omission hallucinations without introducing additional fabrication hallucinations. Our findings reveal a critical oversight in current object hallucination research and chart new directions for developing more robust and balanced hallucination mitigation strategies.
Comment: Matches criterion 2 (Visual and Multimodal Large Language Models) as it addresses hallucination issues in multimodal large language models. Relevance: 9 Novelty: 7
ArXiv ID: 2509.02273 Authors: Yingrui Ji, Jiansheng Chen, Jingbo Chen, Anzhi Yue, Chenhao Wang, Kai Li, Yao Zhu
Abstract: Out-of-distribution (OOD) detection represents a critical challenge in remote sensing applications, where reliable identification of novel or anomalous patterns is essential for autonomous monitoring, disaster response, and environmental assessment. Despite remarkable progress in OOD detection for natural images, existing methods and benchmarks remain poorly suited to remote sensing imagery due to data scarcity, complex multi-scale scene structures, and pronounced distribution shifts. To this end, we propose RS-OOD, a novel framework that leverages remote sensing-specific vision-language modeling to enable robust few-shot OOD detection. Our approach introduces three key innovations: spatial feature enhancement that improved scene discrimination, a dual-prompt alignment mechanism that cross-verifies scene context against fine-grained semantics for spatial-semantic consistency, and a confidence-guided self-training loop that dynamically mines pseudo-labels to expand training data without manual annotation. RS-OOD consistently outperforms existing methods across multiple remote sensing benchmarks and enables efficient adaptation with minimal labeled data, demonstrating the critical value of spatial-semantic integration.
Comment: Matches criteria 2 and 5 as it explores vision-language integration for out-of-distribution detection in remote sensing, leveraging spatial-semantic consistency and novel mechanisms. Relevance: 8 Novelty: 7
ArXiv ID: 2509.00385 Authors: Joohyun Chang, Soyeon Hong, Hyogun Lee, Seong Jong Ha, Dongho Lee, Seong Tae Kim, Jinwoo Choi
Abstract: In this work, we tackle the egocentric visual query localization (VQL), where a model should localize the query object in a long-form egocentric video. Frequent and abrupt viewpoint changes in egocentric videos cause significant object appearance variations and partial occlusions, making it difficult for existing methods to achieve accurate localization. To tackle these challenges, we introduce Hierarchical, Egocentric and RObust Visual Query Localization (HERO-VQL), a novel method inspired by human cognitive process in object recognition. We propose i) Top-down Attention Guidance (TAG) and ii) Egocentric Augmentation based Consistency Training (EgoACT). Top-down Attention Guidance refines the attention mechanism by leveraging the class token for high-level context and principal component score maps for fine-grained localization. To enhance learning in diverse and challenging matching scenarios, EgoAug enhances query diversity by replacing the query with a randomly selected corresponding object from groundtruth annotations and simulates extreme viewpoint changes by reordering video frames. Additionally, CT loss enforces stable object localization across different augmentation scenarios. Extensive experiments on VQ2D dataset validate that HERO-VQL effectively handles egocentric challenges, significantly outperforming baselines.
Comment: Matches criteria 6 as it focuses on video-based tasks, specifically egocentric visual query localization, with novel methodologies. Relevance: 8 Novelty: 7
ArXiv ID: 2509.02544 Authors: Haoming Wang, Haoyang Zou, Huatong Song, Jiazhan Feng, Junjie Fang, Junting Lu, Longxiang Liu, Qinyu Luo, Shihao Liang, Shijue Huang, Wanjun Zhong, Yining Ye, Yujia Qin, Yuwen Xiong, Yuxin Song, Zhiyong Wu, Bo Li, Chen Dun, Chong Liu, Fuxing Leng, Hanbin Wang, Hao Yu, Haobin Chen, Hongyi Guo, Jing Su, Jingjia Huang, Kai Shen, Kaiyu Shi, Lin Yan, Peiyao Zhao, Pengfei Liu, Qinghao Ye, Renjie Zheng, Wayne Xin Zhao, Wen Heng, Wenhao Huang, Wenqian Wang, Xiaobo Qin, Yi Lin, Youbin Wu, Zehui Chen, Zihao Wang, Baoquan Zhong, Xinchun Zhang, Xujing Li, Yuanfan Li, Zhongkai Zhao, Chengquan Jiang, Faming Wu, Haotian Zhou, Jinlin Pang, Li Han, Qianli Ma, Siyao Liu, Songhua Cai, Wenqi Fu, Xin Liu, Zhi Zhang, Bo Zhou, Guoliang Li, Jiajun Shi, Jiale Yang, Jie Tang, Li Li, Taoran Lu, Woyu Lin, Xiaokang Tong, Xinyao Li, Yichi Zhang, Yu Miao, Zhengxuan Jiang, Zili Li, Ziyuan Zhao, Chenxin Li, Dehua Ma, Feng Lin, Ge Zhang, Haihua Yang, Hangyu Guo, Hongda Zhu, Jiaheng Liu, Junda Du, Kai Cai, Kuanye Li, Lichen Yuan, Meilan Han, Minchao Wang, Shuyue Guo, Tianhao Cheng, Xiaobo Ma, Xiaojun Xiao, Xiaolong Huang, Xinjie Chen, Yidi Du, Yilin Chen, Yiwen Wang, Zhaojian Li, Zhenzhu Yang, Zhiyuan Zeng, Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, Guang Shi
Abstract: The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent model that addresses these challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts. Empirical evaluation demonstrates that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5. On GUI benchmarks, it reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld, outperforming strong baselines such as Claude and OpenAI agents. In game environments, it attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and remains competitive with frontier proprietary models (e.g., OpenAI o3) on LMGame-Bench. Additionally, the model can generalize to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. Detailed analyses of training dynamics further provide insights into achieving stability and efficiency in large-scale agent RL. These results underscore UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios.
Comment: Matches criteria 3 as it introduces a new benchmark and methods for GUI agents, addressing challenges in embodied AI. Relevance: 8 Novelty: 7
ArXiv ID: 2509.01275 Authors: Jiahao Li Yang Lu, Yachao Zhang, Fangyong Wang, Yuan Xie, Yanyun Qu
Abstract: Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-vocabulary inference poses challenges in discriminative modeling of latent unseen category. To address this challenge, existing vision-language model (VLM)-based approaches demonstrate commendable performance through pre-trained multi-modal representations. However, the fundamental mechanisms of latent semantic comprehension remain underexplored, making the bottleneck for OVSS. In this work, we initiate a probing experiment to explore distribution patterns and dynamics of latent semantics in VLMs under inductive learning paradigms. Building on these insights, we propose X-Agent, an innovative OVSS framework employing latent semantic-aware ``agent'' to orchestrate cross-modal attention mechanisms, simultaneously optimizing latent semantic dynamic and amplifying its perceptibility. Extensive benchmark evaluations demonstrate that X-Agent achieves state-of-the-art performance while effectively enhancing the latent semantic saliency.
Comment: Matches criterion 5 (Integration of Image/Video and Large Language Models) as it focuses on open-vocabulary semantic segmentation using vision-language models. Relevance: 8 Novelty: 7
ArXiv ID: 2509.00373 Authors: Sihao Wu, Gaojie Jin, Wei Huang, Jianhong Wang, Xiaowei Huang
Abstract: Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has emerged as a promising defence, existing approaches often rely on task-specific contrastive prompts to extract harmful directions, which exhibit suboptimal performance and can degrade visual grounding performance. To address these limitations, we propose \textit{Sequence-Level Preference Optimization} for VLM (\textit{SPO-VLM}), a novel two-stage defense framework that combines activation-level intervention with policy-level optimization to enhance model robustness. In \textit{Stage I}, we compute adaptive layer-specific steering vectors from diverse data sources, enabling generalized suppression of harmful behaviors during inference. In \textit{Stage II}, we refine these steering vectors through a sequence-level preference optimization process. This stage integrates automated toxicity assessment, as well as visual-consistency rewards based on caption-image alignment, to achieve safe and semantically grounded text generation. The two-stage structure of SPO-VLM balances efficiency and effectiveness by combining a lightweight mitigation foundation in Stage I with deeper policy refinement in Stage II. Extensive experiments shown SPO-VLM enhances safety against attacks via activation steering and preference optimization, while maintaining strong performance on benign tasks without compromising visual understanding capabilities. We will release our code, model weights, and evaluation toolkit to support reproducibility and future research. \textcolor{red}{Warning: This paper may contain examples of offensive or harmful text and images.}
Comment: Matches criterion 2 (Visual and Multimodal Large Language Models) as it proposes a novel defense framework for vision-language models, focusing on robustness and safety. Relevance: 8 Novelty: 7
ArXiv ID: 2509.01610 Authors: Jefferson Hernandez, Jing Shi, Simon Jenni, Vicente Ordonez, Kushal Kafle
Abstract: Traditional alignment methods for Large Vision and Language Models (LVLMs) primarily rely on human-curated preference data. Human-generated preference data is costly; machine-generated preference data is limited in quality; and self-supervised preference data often introduces hallucinations. To overcome these limitations, we propose a novel Panel-of-Peers learning framework inspired by collaborative learning among humans. This approach leverages a panel of LVLMs, each evaluating and learning from their collective outputs through an iterative self-improvement process. By simulating a peer review system, our models generate, assess, and refine outputs in response to a curated set of prompts, mimicking a classroom learning environment. We demonstrate that this methodology enhances model performance without requiring extensive human-labeled datasets. Our experiments show significant improvement across multiple benchmarks, demonstrating the potential of peer evaluations as a scalable alternative to self-supervised alignment. Notably, we show that Panel-of-Peers increases the average score on fifteen benchmarks from 48% to 57%
Comment: Matches criteria 2 as it focuses on improving large vision and language models through a novel peer-learning framework. Relevance: 8 Novelty: 7
ArXiv ID: 2509.02545 Authors: Xinrui Gong, Oliver Hahn, Christoph Reich, Krishnakant Singh, Simone Schaub-Meyer, Daniel Cremers, Stefan Roth
Abstract: Unsupervised multi-object discovery (MOD) aims to detect and localize distinct object instances in visual scenes without any form of human supervision. Recent approaches leverage object-centric learning (OCL) and motion cues from video to identify individual objects. However, these approaches use supervision to generate pseudo labels to train the OCL model. We address this limitation with MR-DINOSAUR -- Motion-Refined DINOSAUR -- a minimalistic unsupervised approach that extends the self-supervised pre-trained OCL model, DINOSAUR, to the task of unsupervised multi-object discovery. We generate high-quality unsupervised pseudo labels by retrieving video frames without camera motion for which we perform motion segmentation of unsupervised optical flow. We refine DINOSAUR's slot representations using these pseudo labels and train a slot deactivation module to assign slots to foreground and background. Despite its conceptual simplicity, MR-DINOSAUR achieves strong multi-object discovery results on the TRI-PD and KITTI datasets, outperforming the previous state of the art despite being fully unsupervised.
Comment: Matches criteria 3 as it introduces a novel unsupervised method for multi-object discovery in visual scenes. Relevance: 8 Novelty: 7
ArXiv ID: 2509.01554 Authors: Hao-Chih Lee, Zelong Liu, Hamza Ahmed, Spencer Kim, Sean Huver, Vishwesh Nath, Zahi A. Fayad, Timothy Deyer, Xueyan Mei
Abstract: General-purpose vision-language models (VLMs) have emerged as promising tools in radiology, offering zero-shot capabilities that mitigate the need for large labeled datasets. However, in high-stakes domains like diagnostic radiology, these models often lack the discriminative precision required for reliable clinical use. This challenge is compounded by the scarcity and heterogeneity of publicly available volumetric CT datasets, which vary widely in annotation formats and granularity. To address these limitations, we introduce Uniferum, a volumetric VLM that unifies diverse supervision signals, encoded in classification labels and segmentation masks, into a single training framework. By harmonizing three public 3D CT datasets with distinct annotations, Uniferum achieves state-of-the-art performance, improving AUROC on the CT-RATE benchmark by 7% compared to CLIP-based and conventional multi-label convolutional models. The model demonstrates robust out-of-distribution generalization, with observed evidence of unexpected zero-shot performance on the RAD-CHEST and INSPECT datasets. Our results highlight the effectiveness of integrating heterogeneous annotations and body segmentation to enhance model performance, setting a new direction for clinically reliable, data-efficient VLMs in 3D medical imaging.
Comment: Matches criteria 2 and 5 as it focuses on vision-language models in 3D medical imaging with novel training strategies. Relevance: 8 Novelty: 7
ArXiv ID: 2509.01986 Authors: Ziyun Zeng, Junhao Zhang, Wei Li, Mike Zheng Shou
Abstract: In recent years, integrating multimodal understanding and generation into a single unified model has emerged as a promising paradigm. While this approach achieves strong results in text-to-image (T2I) generation, it still struggles with precise image editing. We attribute this limitation to an imbalanced division of responsibilities. The understanding module primarily functions as a translator that encodes user instructions into semantic conditions, while the generation module must simultaneously act as designer and painter, inferring the original layout, identifying the target editing region, and rendering the new content. This imbalance is counterintuitive because the understanding module is typically trained with several times more data on complex reasoning tasks than the generation module. To address this issue, we introduce Draw-In-Mind (DIM), a dataset comprising two complementary subsets: (i) DIM-T2I, containing 14M long-context image-text pairs to enhance complex instruction comprehension; and (ii) DIM-Edit, consisting of 233K chain-of-thought imaginations generated by GPT-4o, serving as explicit design blueprints for image edits. We connect a frozen Qwen2.5-VL-3B with a trainable SANA1.5-1.6B via a lightweight two-layer MLP, and train it on the proposed DIM dataset, resulting in DIM-4.6B-T2I/Edit. Despite its modest parameter scale, DIM-4.6B-Edit achieves SOTA or competitive performance on the ImgEdit and GEdit-Bench benchmarks, outperforming much larger models such as UniWorld-V1 and Step1X-Edit. These findings demonstrate that explicitly assigning the design responsibility to the understanding module provides significant benefits for image editing. Our dataset and models will be available at https://github.com/showlab/DIM.
Comment: Matches criterion 5 as it integrates multimodal understanding and generation for precise image editing. Relevance: 8 Novelty: 7
ArXiv ID: 2509.01177 Authors: Junxiang Liu, Junming Lin, Jiangtong Li, Jie Li
Abstract: Reconstruction dynamic visual scenes from electroencephalography (EEG) signals remains a primary challenge in brain decoding, limited by the low spatial resolution of EEG, a temporal mismatch between neural recordings and video dynamics, and the insufficient use of semantic information within brain activity. Therefore, existing methods often inadequately resolve both the dynamic coherence and the complex semantic context of the perceived visual stimuli. To overcome these limitations, we introduce DynaMind, a novel framework that reconstructs video by jointly modeling neural dynamics and semantic features via three core modules: a Regional-aware Semantic Mapper (RSM), a Temporal-aware Dynamic Aligner (TDA), and a Dual-Guidance Video Reconstructor (DGVR). The RSM first utilizes a regional-aware encoder to extract multimodal semantic features from EEG signals across distinct brain regions, aggregating them into a unified diffusion prior. In the mean time, the TDA generates a dynamic latent sequence, or blueprint, to enforce temporal consistency between the feature representations and the original neural recordings. Together, guided by the semantic diffusion prior, the DGVR translates the temporal-aware blueprint into a high-fidelity video reconstruction. On the SEED-DV dataset, DynaMind sets a new state-of-the-art (SOTA), boosting reconstructed video accuracies (video- and frame-based) by 12.5 and 10.3 percentage points, respectively. It also achieves a leap in pixel-level quality, showing exceptional visual fidelity and temporal coherence with a 9.4% SSIM improvement and a 19.7% FVMD reduction. This marks a critical advancement, bridging the gap between neural dynamics and high-fidelity visual semantics.
Comment: Matches criterion 5 as it combines video understanding and multimodal semantics with neural dynamics for video reconstruction. Relevance: 8 Novelty: 7
ArXiv ID: 2509.00074 Authors: C'edric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman, Jacob Andreas, Joshua Tenenbaum
Abstract: The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a probabilistic model of how humans share advice conditioned on their beliefs, allowing our agents both to generate advice for others and to interpret linguistic input as evidence during Bayesian inference. Using behavioral experiments and simulations across 10 video games, we show how linguistic guidance can shape exploration and accelerate learning by reducing risky interactions and speeding up key discoveries in both humans and models. We further explore how knowledge can accumulate across generations through iterated learning experiments and demonstrate successful knowledge transfer between humans and models -- revealing how structured, language-compatible representations might enable human-machine collaborative learning.
Comment: Matches criterion 1 (Spatial Intelligence and Embodied Agents) as it models social learning in complex tasks, integrating linguistic and sensorimotor data. Relevance: 8 Novelty: 7
ArXiv ID: 2509.00969 Authors: Xiangchen Wang, Jinrui Zhang, Teng Wang, Haigang Zhang, Feng Zheng
Abstract: Recent advancements in large video-language models have revolutionized video understanding tasks. However, their efficiency is significantly constrained by processing high volumes of visual tokens. Existing token compression strategies apply a fixed compression ratio, ignoring the variability in semantic density among different video clips. Consequently, this lead to inadequate representation of information-rich clips due to insufficient tokens and unnecessary computation on static or content-poor ones. To address this, we propose LangDC, a Language-aware Dynamic Token Compressor. LangDC leverages a lightweight language model to describe video clips, converting them into soft caption tokens as visual representations. Trained with our proposed semantic density-aware supervision, LangDC aims to 1) cover key visual cues necessary for downstream task reasoning and 2) dynamically adjust compression ratios based on scene richness, reflected by descriptions length. Our design mimics how humans dynamically express what they see: complex scenes (seeing more) elicit more detailed language to convey nuances (saying more), whereas simpler scenes are described with fewer words. Experimental results show that our method reduces FLOPs by 49% compared to VideoGPT+ while maintaining competitive performance. Furthermore, qualitative results demonstrate our approach adaptively adjusts the token compression ratio based on video segment richness.
Comment: Matches criterion 6 (Video Understanding) as it proposes a novel method for dynamic token compression in video understanding tasks. Relevance: 8 Novelty: 7
ArXiv ID: 2509.01405 Authors: Jianman Lin, Tianshui Chen, Chunmei Qing, Zhijing Yang, Shuangping Huang, Yuheng Ren, Liang Lin
Abstract: Maintaining stylistic consistency is crucial for the cohesion and aesthetic appeal of images, a fundamental requirement in effective image editing and inpainting. However, existing methods primarily focus on the semantic control of generated content, often neglecting the critical task of preserving this consistency. In this work, we introduce the Neural Scene Designer (NSD), a novel framework that enables photo-realistic manipulation of user-specified scene regions while ensuring both semantic alignment with user intent and stylistic consistency with the surrounding environment. NSD leverages an advanced diffusion model, incorporating two parallel cross-attention mechanisms that separately process text and style information to achieve the dual objectives of semantic control and style consistency. To capture fine-grained style representations, we propose the Progressive Self-style Representational Learning (PSRL) module. This module is predicated on the intuitive premise that different regions within a single image share a consistent style, whereas regions from different images exhibit distinct styles. The PSRL module employs a style contrastive loss that encourages high similarity between representations from the same image while enforcing dissimilarity between those from different images. Furthermore, to address the lack of standardized evaluation protocols for this task, we establish a comprehensive benchmark. This benchmark includes competing algorithms, dedicated style-related metrics, and diverse datasets and settings to facilitate fair comparisons. Extensive experiments conducted on our benchmark demonstrate the effectiveness of the proposed framework.
Comment: Matches criteria 4 as it introduces a novel framework for semantic image manipulation with a focus on style consistency, leveraging advanced diffusion models. Relevance: 7 Novelty: 7
ArXiv ID: 2509.02444 Authors: Jingru Fan, Yufan Dang, Jingyao Wu, Huatao Li, Runde Yang, Xiyuan Yang, Yuheng Wang, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Dahai Li, Chen Qian
Abstract: With the raid evolution of large language models and multimodal foundation models, the mobile-agent landscape has proliferated without converging on the fundamental challenges. This paper identifies four core problems that must be solved for mobile agents to deliver practical, scalable impact: (1) generalization across tasks, modalities, apps, and devices; (2) accuracy, specifically precise on-screen interaction and click targeting; (3) long-horizon capability for sustained, multi-step goals; and (4) efficiency, specifically high-performance runtime on resource-constrained devices. We present AppCopilot, a multimodal, multi-agent, general-purpose on-device assistant that operates across applications and constitutes a full-stack, closed-loop system from data to deployment. AppCopilot operationalizes this position through an end-to-end autonomous pipeline spanning data collection, training, deployment, high-quality and efficient inference, and mobile application development. At the model layer, it integrates multimodal foundation models with robust Chinese-English support. At the reasoning and control layer, it combines chain-of-thought reasoning, hierarchical task planning and decomposition, and multi-agent collaboration. At the execution layer, it enables user personalization and experiential adaptation, voice interaction, function calling, cross-app and cross-device orchestration, and comprehensive mobile app support. The system design incorporates profiling-driven optimization for latency, memory, and energy across heterogeneous hardware. Empirically, AppCopilot achieves significant improvements along all four dimensions: stronger generalization, higher-precision on-screen actions, more reliable long-horizon task completion, and faster, more resource-efficient runtime.
Comment: Matches criterion 3 as it introduces a new benchmark and methods for embodied AI in mobile agents. Relevance: 7 Novelty: 7
ArXiv ID: 2509.00419 Authors: Lianyu Hu, Fanhua Shang, Wei Feng, Liang Wan
Abstract: In this paper, we introduce LightVLM, a simple but effective method that can be seamlessly deployed upon existing Vision-Language Models (VLMs) to greatly accelerate the inference process in a training-free manner. We divide the inference procedure of VLMs into two stages, i.e., encoding and decoding, and propose to simultaneously accelerate VLMs in both stages to largely improve model efficiency. During encoding, we propose pyramid token merging to reduce tokens of different LLM layers in a hierarchical manner by finally only keeping a few dominant tokens to achieve high efficiency. During decoding, aimed at reducing the high latency of outputting long sequences, we propose KV Cache compression to remove unnecessary caches to increase the network throughput. Experimental results show that LightVLM successfully retains 100% performance when only preserving 35% image tokens, and maintains around 98% performance when keeping only 3% image tokens. LightVLM could 2.02$\times$ the network throughput and reduce the prefilling time by 3.65$\times$. LightVLM also makes large VLMs faster again by enabling a heavy model (e.g., InternVL2.5 26B) to infer faster than significantly smaller models (e.g., InternVL2.5 8B), hopefully facilitating the real-world deployment. When generating long text sequences (e.g., 4096 tokens), LightVLM could reduce the inference time by 3.21$\times$, largely outperforming existing methods.
Comment: Matches criterion 2 as it introduces a method to accelerate Vision-Language Models (VLLMs) with novel strategies. Relevance: 7 Novelty: 7
ArXiv ID: 2509.00665 Authors: Weilong Yan, Xin Zhang, Robby T. Tan
Abstract: Monocular depth estimation under adverse weather conditions (e.g.\ rain, fog, snow, and nighttime) remains highly challenging due to the lack of reliable ground truth and the difficulty of learning from unlabeled real-world data. Existing methods often rely on synthetic adverse data with pseudo-labels, which suffer from domain gaps, or employ self-supervised learning, which violates photometric assumptions in adverse scenarios. In this work, we propose to achieve weather--generalized depth estimation by Parameter--Efficient Fine--Tuning (PEFT) of Vision Foundation Models (VFMs), using only a small amount of high--visibility (normal) data. While PEFT has shown strong performance in semantic tasks such as segmentation, it remains underexplored for geometry--centric tasks like depth estimation -- especially in terms of balancing effective adaptation with the preservation of pretrained knowledge. To this end, we introduce the Selecting--Tuning--Maintaining (STM) strategy, which structurally decomposes the pretrained weights of VFMs based on two kinds of effective ranks (entropy--rank and stable--rank). In the tuning phase, we adaptively select the proper rank number as well as the task--aware singular directions for initialization, based on the entropy--rank and full--tuned weight; while in the maintaining stage, we enforce a principal direction regularization based on the stable--rank. This design guarantees flexible task adaptation while preserving the strong generalization capability of the pretrained VFM. Extensive experiments on four real--world benchmarks across diverse weather conditions demonstrate that STM not only outperforms existing PEFT methods and full fine--tuning but also surpasses methods trained with adverse synthetic data, and even the depth foundation model
Comment: Matches criterion 4 (Vision Foundation Models and Their Applications) as it focuses on parameter-efficient fine-tuning of vision foundation models for depth estimation under adverse weather conditions. Relevance: 7 Novelty: 6
ArXiv ID: 2509.01383 Authors: Long Zhang, Peipei Song, Jianfeng Dong, Kun Li, Xun Yang
Abstract: Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos partially relevant to a given query. The core challenge lies in learning robust query-video alignment against spurious semantic correlations arising from inherent data uncertainty: 1) query ambiguity, where the query incompletely characterizes the target video and often contains uninformative tokens, and 2) partial video relevance, where abundant query-irrelevant segments introduce contextual noise in cross-modal alignment. Existing methods often focus on enhancing multi-scale clip representations and retrieving the most relevant clip. However, the inherent data uncertainty in PRVR renders them vulnerable to distractor videos with spurious similarities, leading to suboptimal performance. To fill this research gap, we propose Robust Alignment Learning (RAL) framework, which explicitly models the uncertainty in data. Key innovations include: 1) we pioneer probabilistic modeling for PRVR by encoding videos and queries as multivariate Gaussian distributions. This not only quantifies data uncertainty but also enables proxy-level matching to capture the variability in cross-modal correspondences; 2) we consider the heterogeneous informativeness of query words and introduce learnable confidence gates to dynamically weight similarity. As a plug-and-play solution, RAL can be seamlessly integrated into the existing architectures. Extensive experiments across diverse retrieval backbones demonstrate its effectiveness.
Comment: Matches criterion 6 as it focuses on video retrieval with robust alignment learning, advancing video understanding. Relevance: 7 Novelty: 6
ArXiv ID: 2509.01317 Authors: Alexandros Gkillas, Nikos Piperigkos, Aris S. Lalos
Abstract: High-resolution LiDAR data plays a critical role in 3D semantic segmentation for autonomous driving, but the high cost of advanced sensors limits large-scale deployment. In contrast, low-cost sensors such as 16-channel LiDAR produce sparse point clouds that degrade segmentation accuracy. To overcome this, we introduce the first end-to-end framework that jointly addresses LiDAR super-resolution (SR) and semantic segmentation. The framework employs joint optimization during training, allowing the SR module to incorporate semantic cues and preserve fine details, particularly for smaller object classes. A new SR loss function further directs the network to focus on regions of interest. The proposed lightweight, model-based SR architecture uses significantly fewer parameters than existing LiDAR SR approaches, while remaining easily compatible with segmentation networks. Experiments show that our method achieves segmentation performance comparable to models operating on high-resolution and costly 64-channel LiDAR data.
Comment: Matches criterion 3 as it introduces a novel method for LiDAR super-resolution and segmentation, which is relevant to embodied/robotic AI. Relevance: 7 Novelty: 6
ArXiv ID: 2509.01028 Authors: Zixin Zhu, Kevin Duarte, Mamshad Nayeem Rizve, Chengyuan Xu, Ratheesh Kalarot, Junsong Yuan
Abstract: In text-to-image (T2I) generation, achieving fine-grained control over attributes - such as age or smile - remains challenging, even with detailed text prompts. Slider-based methods offer a solution for precise control of image attributes. Existing approaches typically train individual adapter for each attribute separately, overlooking the entanglement among multiple attributes. As a result, interference occurs among different attributes, preventing precise control of multiple attributes together. To address this challenge, we aim to disentangle multiple attributes in slider-based generation to enbale more reliable and independent attribute manipulation. Our approach, CompSlider, can generate a conditional prior for the T2I foundation model to control multiple attributes simultaneously. Furthermore, we introduce novel disentanglement and structure losses to compose multiple attribute changes while maintaining structural consistency within the image. Since CompSlider operates in the latent space of the conditional prior and does not require retraining the foundation model, it reduces the computational burden for both training and inference. We evaluate our approach on a variety of image attributes and highlight its generality by extending to video generation.
Comment: Matches criterion 5 (Integration of Image/Video and Large Language Models) as it focuses on disentangled attribute manipulation in text-to-image generation. Relevance: 7 Novelty: 6
ArXiv ID: 2509.02029 Authors: Nikolaos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki
Abstract: This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the adage "fake it till you make it". While contrastive self-supervised learning has achieved remarkable success, it typically relies on vast amounts of real-world data and carefully curated hard negatives. To explore alternatives to these requirements, we investigate two forms of "faking it" in vision transformers. First, we study the potential of generative models for unsupervised representation learning, leveraging synthetic data to augment sample diversity. Second, we examine the feasibility of generating synthetic hard negatives in the representation space, creating diverse and challenging contrasts. Our framework - dubbed Syn2Co - combines both approaches and evaluates whether synthetically enhanced training can lead to more robust and transferable visual representations on DeiT-S and Swin-T architectures. Our findings highlight the promise and limitations of synthetic data in self-supervised learning, offering insights for future work in this direction.
Comment: Matches criteria 4 as it focuses on self-supervised learning in vision transformers, leveraging synthetic data and synthetic hard negatives. Relevance: 6 Novelty: 6
ArXiv ID: 2509.02547 Authors: Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai
Abstract: The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.
Comment: Matches criteria 7 as it is a comprehensive survey on Agentic Reinforcement Learning for LLMs, synthesizing the state of the art and highlighting challenges. Relevance: 5 Novelty: 7
ArXiv ID: 2509.00177 Authors: Faizan Farooq Khan, Vladan Stojni'c, Zakaria Laskar, Mohamed Elhoseiny, Giorgos Tolias
Abstract: This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant regions in the representation space, limiting retrieval performance. To bridge this modality gap, we propose a two-step approach. First, we transform the text query into a visual query using a generative diffusion model. Then, we estimate image-to-image similarity with a vision model. Additionally, we introduce an aggregation network that combines multiple generated images into a single vector representation and fuses similarity scores across both query modalities. Our approach leverages advancements in vision encoders, VLMs, and text-to-image generation models. Extensive evaluations show that it consistently outperforms retrieval methods relying solely on text queries. Source code is available at: https://github.com/faixan-khan/cletir
Comment: Matches criterion 5 as it combines text-to-image retrieval with vision encoders and diffusion models. Relevance: 6 Novelty: 6
ArXiv ID: 2509.00598 Authors: Boyi Li, Ce Zhang, Richard M. Timmerman, Wenxuan Bao
Abstract: The emergence of vision language models (VLMs) has bridged vision and language, enabling joint multimodal understanding beyond traditional visual-only deep learning models. However, transferring VLMs from the natural image domain to remote sensing (RS) segmentation remains challenging due to the limited category diversity in RS datasets and the domain gap between natural and RS imagery. Here, we propose a training-free framework, DGL-RSIS, that decouples visual and textual inputs, performing visual-language alignment at both the local semantic and global contextual levels through tailored strategies. Specifically, we first introduce a global-local decoupling (GLD) module, where text inputs are divided into local class nouns and global modifiers using natural language processing (NLP) techniques; image inputs are partitioned into a set of class-agnostic mask proposals via unsupervised mask proposal networks. Second, visual and textual features are aligned at local scale, through a novel context-aware cropping strategy for extracting image patches with proper boundaries and introducing RS-specific knowledge to enrich the text inputs. By matching the enhanced text features with mask-guided visual features, we enable the mask classification, supporting open-vocabulary semantic segmentation (OVSS). Third, at the global scale, we propose a Cross-Scale Grad-CAM module to refine Grad-CAM maps using contextual information from global modifiers. A subsequent mask selection module integrates pixel-level Grad-CAM activations into the mask-level segmentation output, such that accurate and interpretable alignment can be realized across global and local dimensions for referring expression segmentation (RES).
Comment: Matches criterion 1 as it focuses on spatial intelligence and reasoning in remote sensing image segmentation. Relevance: 6 Novelty: 6
ArXiv ID: 2509.01338 Authors: Francesca Cairoli, Luca Bortolussi, Jyotirmoy V. Deshmukh, Lars Lindemann, Nicola Paoletti
Abstract: We consider the problem of quantitative predictive monitoring (QPM) of stochastic systems, i.e., predicting at runtime the degree of satisfaction of a desired temporal logic property from the current state of the system. Since computational efficiency is key to enable timely intervention against predicted violations, several state-of-the-art QPM approaches rely on fast machine-learning surrogates to provide prediction intervals for the satisfaction values, using conformal inference to offer statistical guarantees. However, these QPM methods suffer when the monitored agent exhibits multi-modal dynamics, whereby certain modes may yield high satisfaction values while others critically violate the property. Existing QPM methods are mode-agnostic and so would yield overly conservative and uninformative intervals that lack meaningful mode-specific satisfaction information. To address this problem, we present GenQPM, a method that leverages deep generative models, specifically score-based diffusion models, to reliably approximate the probabilistic and multi-modal system dynamics without requiring explicit model access. GenQPM employs a mode classifier to partition the predicted trajectories by dynamical mode. For each mode, we then apply conformal inference to produce statistically valid, mode-specific prediction intervals. We demonstrate the effectiveness of GenQPM on a benchmark of agent navigation and autonomous driving tasks, resulting in prediction intervals that are significantly more informative (less conservative) than mode-agnostic baselines.
Comment: Matches criterion 6 as it addresses predictive monitoring in multi-modal scenarios, relevant to video understanding. Relevance: 5 Novelty: 6
ArXiv ID: 2509.00578 Authors: Abdellah Zakaria Sellam, Ilyes Benaissa, Salah Eddine Bekhouche, Abdenour Hadid, Vito Ren'o, Cosimo Distante
Abstract: Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through conditional denoising diffusion, its performance remains limited by local feature conditioning in context-dependent scenarios. We address this fundamental limitation by introducing Context-Aware Fusion (CAF), which leverages cross-attention mechanisms to integrate global scene context with local proposal features directly. The global context is generated using a separate dedicated encoder that captures comprehensive environmental information, enabling each object proposal to attend to scene-level understanding. Our framework significantly enhances the generative detection paradigm by enabling each object proposal to attend to comprehensive environmental information. Experimental results demonstrate an improvement over state-of-the-art models on the CarDD benchmark, establishing new performance benchmarks for context-aware object detection in fine-grained domains
Comment: Matches criterion 4 as it focuses on enhancing object detection using generative denoising and global scene context. Relevance: 5 Novelty: 6
ArXiv ID: 2509.01259 Authors: Thinh-Phuc Nguyen, Thanh-Hai Nguyen, Gia-Huy Dinh, Lam-Huy Nguyen, Minh-Triet Tran, Trung-Nghia Le
Abstract: Image captioning systems often produce generic descriptions that fail to capture event-level semantics which are crucial for applications like news reporting and digital archiving. We present ReCap, a novel pipeline for event-enriched image retrieval and captioning that incorporates broader contextual information from relevant articles to generate narrative-rich, factually grounded captions. Our approach addresses the limitations of standard vision-language models that typically focus on visible content while missing temporal, social, and historical contexts. ReCap comprises three integrated components: (1) a robust two-stage article retrieval system using DINOv2 embeddings with global feature similarity for initial candidate selection followed by patch-level mutual nearest neighbor similarity re-ranking; (2) a context extraction framework that synthesizes information from article summaries, generic captions, and original source metadata; and (3) a large language model-based caption generation system with Semantic Gaussian Normalization to enhance fluency and relevance. Evaluated on the OpenEvents V1 dataset as part of Track 1 in the EVENTA 2025 Grand Challenge, ReCap achieved a strong overall score of 0.54666, ranking 2nd on the private test set. These results highlight ReCap's effectiveness in bridging visual perception with real-world knowledge, offering a practical solution for context-aware image understanding in high-stakes domains. The code is available at https://github.com/Noridom1/EVENTA2025-Event-Enriched-Image-Captioning.
Comment: Matches criterion 2 as it explores a novel pipeline for vision-language integration in image captioning. Relevance: 5 Novelty: 6
ArXiv ID: 2509.00751 Authors: Dinh-Khoi Vo, Van-Loc Nguyen, Minh-Triet Tran, Trung-Nghia Le
Abstract: Event-based image retrieval from free-form captions presents a significant challenge: models must understand not only visual features but also latent event semantics, context, and real-world knowledge. Conventional vision-language retrieval approaches often fall short when captions describe abstract events, implicit causality, temporal context, or contain long, complex narratives. To tackle these issues, we introduce a multi-stage retrieval framework combining dense article retrieval, event-aware language model reranking, and efficient image collection, followed by caption-guided semantic matching and rank-aware selection. We leverage Qwen3 for article search, Qwen3-Reranker for contextual alignment, and Qwen2-VL for precise image scoring. To further enhance performance and robustness, we fuse outputs from multiple configurations using Reciprocal Rank Fusion (RRF). Our system achieves the top-1 score on the private test set of Track 2 in the EVENTA 2025 Grand Challenge, demonstrating the effectiveness of combining language-based reasoning and multimodal retrieval for complex, real-world image understanding. The code is available at https://github.com/vdkhoi20/EVENT-Retriever.
Comment: Matches criterion 2 as it focuses on multimodal image retrieval with event-aware language models, relevant to vision-language integration. Relevance: 6 Novelty: 5
ArXiv ID: 2509.01984 Authors: Quan Dao, Xiaoxiao He, Ligong Han, Ngan Hoai Nguyen, Amin Heyrani Nobar, Faez Ahmed, Han Zhang, Viet Anh Nguyen, Dimitris Metaxas
Abstract: Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation tasks. While conditional generation has been widely explored, the ability to perform prompt-guided image editing without additional training is equally critical, as it supports numerous practical real-world applications. This paper investigates the text-to-image editing capabilities of VAR by introducing Visual AutoRegressive Inverse Noise (VARIN), the first noise inversion-based editing technique designed explicitly for VAR models. VARIN leverages a novel pseudo-inverse function for argmax sampling, named Location-aware Argmax Inversion (LAI), to generate inverse Gumbel noises. These inverse noises enable precise reconstruction of the source image and facilitate targeted, controllable edits aligned with textual prompts. Extensive experiments demonstrate that VARIN effectively modifies source images according to specified prompts while significantly preserving the original background and structural details, thus validating its efficacy as a practical editing approach.
Comment: Matches criterion 5 as it introduces a novel noise inversion technique for text-based image editing using autoregressive models. Relevance: 5 Novelty: 6
ArXiv ID: 2509.01552 Authors: Junjie Chen, Xuyang Liu, Zichen Wen, Yiyu Wang, Siteng Huang, Honggang Chen
Abstract: Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts, leading to reduced inference efficiency. Token compression offers a direct solution by reducing the number of tokens to be processed, thereby improving computational efficiency. Through extensive analysis, we identify two critical limitations in existing inner-LLM token compression methods: positional bias and incompatibility with efficient operators, which hinder their practical deployment for LVLM acceleration. This paper presents the first approach from a token variation perspective, revealing that visual token variations within LLMs exhibit task-agnostic properties. We propose Variation-aware Vision Token Dropping (\textit{i.e.}, \textbf{V$^2$Drop}), which progressively removes visual tokens with minimal variation during LVLM inference, thereby enhancing computational efficiency. Extensive experiments across multiple models and benchmarks demonstrate that our V$^2$Drop is able to maintain \textbf{94.0%} and \textbf{98.6%} of the original model performance for image and video understanding tasks respectively, while reducing LLM generation latency by \textbf{31.5%} and \textbf{74.2%}. When combined with efficient operators, V$^2$Drop further reduces GPU peak memory usage.
Comment: Matches criterion 2 as it introduces a token-dropping method to improve efficiency in large vision-language models. Relevance: 5 Novelty: 6
ArXiv ID: 2509.01895 Authors: Miguel Esparza, Archit Gupta, Ali Mostafavi, Kai Yin, Yiming Xiao
Abstract: The escalating intensity and frequency of wildfires demand innovative computational methods for rapid and accurate property damage assessment. Traditional methods are often time consuming, while modern computer vision approaches typically require extensive labeled datasets, hindering immediate post-disaster deployment. This research introduces a novel, zero-shot framework leveraging pre-trained vision language models (VLMs) to classify damage from ground-level imagery. We propose and evaluate two pipelines applied to the 2025 Eaton and Palisades fires in California, a VLM (Pipeline A) and a VLM + large language model (LLM) approach (Pipeline B), that integrate structured prompts based on specific wildfire damage indicators. A primary scientific contribution of this study is demonstrating the VLMs efficacy in synthesizing information from multiple perspectives to identify nuanced damage, a critical limitation in existing literature. Our findings reveal that while single view assessments struggled to classify affected structures (F1 scores ranging from 0.225 to 0.511), the multi-view analysis yielded dramatic improvements (F1 scores ranging from 0.857 to 0.947). Moreover, the McNemar test confirmed that pipelines with a multi-view image assessment yields statistically significant classification improvements; however, the improvements this research observed between Pipeline A and B were not statistically significant. Thus, future research can explore the potential of LLM prompting in damage assessment. The practical contribution is an immediately deployable, flexible, and interpretable workflow that bypasses the need for supervised training, significantly accelerating triage and prioritization for disaster response practitioners.
Comment: Matches criterion 5 as it showcases a technique combining vision-language models for multi-view wildfire damage assessment. Relevance: 5 Novelty: 6
ArXiv ID: 2509.00905 Authors: Yutong Gao, Maoyuan Shao, Xinyang Huang, Chuang Zhu, Lijuan Sun, Yu Weng, Xuan Liu, Guoshun Nan
Abstract: CLIP's success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components introduce noise and incur unnecessary computational costs. In this work, we propose Spotlighter, a lightweight token-selection framework that simultaneously enhances accuracy and efficiency in prompt tuning. Spotlighter evaluates each visual token's activation from both sample-wise and semantic-wise perspectives and retains only the top-scoring tokens for downstream prediction. A class-specific semantic memory bank of learned prototypes refines this selection, ensuring semantic representativeness and compensating for discarded features. To further prioritize informative signals, we introduce a two-level ranking mechanism that dynamically weights token--prototype interactions. Across 11 few-shot benchmarks, Spotlighter outperforms CLIP by up to 11.19% in harmonic mean accuracy and achieves up to 0.8K additional FPS, with only 21 extra parameters. These results establish Spotlighter as an effective and scalable baseline for prompt tuning. Code for our method will be available at https://github.com/greatest-gourmet/Spotlighter.
Comment: Matches criterion 2 as it proposes a novel token-selection framework for improving cross-modal semantic alignment in vision-language models. Relevance: 5 Novelty: 6
ArXiv ID: 2509.01868 Authors: Komala Subramanyam Cherukuri, Kewei Sha, Zhenhua Huang
Abstract: Object detection is crucial for Connected Autonomous Vehicles (CAVs) to perceive their surroundings and make safe driving decisions. Centralized training of object detection models often achieves promising accuracy, fast convergence, and simplified training process, but it falls short in scalability, adaptability, and privacy-preservation. Federated learning (FL), by contrast, enables collaborative, privacy-preserving, and continuous training across naturally distributed CAV fleets. However, deploying FL in real-world CAVs remains challenging due to the substantial computational demands of training and inference, coupled with highly diverse operating conditions. Practical deployment must address three critical factors: (i) heterogeneity from non-IID data distributions, (ii) constrained onboard computing hardware, and (iii) environmental variability such as lighting and weather, alongside systematic evaluation to ensure reliable performance. This work introduces the first holistic deployment-oriented evaluation of FL-based object detection in CAVs, integrating model performance, system-level resource profiling, and environmental robustness. Using state-of-the-art detectors, YOLOv5, YOLOv8, YOLOv11, and Deformable DETR, evaluated on the KITTI, BDD100K, and nuScenes datasets, we analyze trade-offs between detection accuracy, computational cost, and resource usage under diverse resolutions, batch sizes, weather and lighting conditions, and dynamic client participation, paving the way for robust FL deployment in CAVs.
Comment: Matches criterion 3 as it introduces a deployment-oriented evaluation for federated object detection in autonomous vehicles, addressing challenges in embodied AI. Relevance: 5 Novelty: 6
ArXiv ID: 2509.00543 Authors: Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci, Zhe Han, Yunpeng Zhang
Abstract: This paper presents the development of an AI-powered workflow that uses Large Language Models (LLMs) to assist in drafting schematic architectural floor plans from natural language prompts. The proposed system interprets textual input to automatically generate layout options including walls, doors, windows, and furniture arrangements. It combines prompt engineering, a furniture placement refinement algorithm, and Python scripting to produce spatially coherent draft plans compatible with design tools such as Autodesk Revit. A case study of a mid-sized residential layout demonstrates the approach's ability to generate functional and structured outputs with minimal manual effort. The workflow is designed for transparent replication, with all key prompt specifications documented to enable independent implementation by other researchers. In addition, the generated models preserve the full range of Revit-native parametric attributes required for direct integration into professional BIM processes.
Comment: Matches criterion 1 as it presents a novel method for spatial reasoning in architectural floor plan generation using LLMs. Relevance: 5 Novelty: 6
ArXiv ID: 2509.01441 Authors: Deyu Zhou, Yuqi Hou, Xiao Xue, Xudong Lu, Qingzhong Li, Lizhen Cui
Abstract: As the social environment is growing more complex and collaboration is deepening, factors affecting the healthy development of service ecosystem are constantly changing and diverse, making its governance a crucial research issue. Applying the scenario analysis method and conducting scenario rehearsals by constructing an experimental system before managers make decisions, losses caused by wrong decisions can be largely avoided. However, it relies on predefined rules to construct scenarios and faces challenges such as limited information, a large number of influencing factors, and the difficulty of measuring social elements. These challenges limit the quality and efficiency of generating social and uncertain scenarios for the service ecosystem. Therefore, we propose a scenario generator design method, which adaptively coordinates three Large Language Model (LLM) empowered agents that autonomously optimize experimental schemes to construct an experimental system and generate high quality scenarios. Specifically, the Environment Agent (EA) generates social environment including extremes, the Social Agent (SA) generates social collaboration structure, and the Planner Agent (PA) couples task-role relationships and plans task solutions. These agents work in coordination, with the PA adjusting the experimental scheme in real time by perceiving the states of each agent and these generating scenarios. Experiments on the ProgrammableWeb dataset illustrate our method generates more accurate scenarios more efficiently, and innovatively provides an effective way for service ecosystem governance related experimental system construction.
Comment: Matches criterion 3 as it introduces a novel simulation framework for LLM-empowered agents in scenario generation, which could be relevant to embodied AI. Relevance: 5 Novelty: 6
ArXiv ID: 2509.00559 Authors: Xuhui Zhou, Jiarui Liu, Akhila Yerukola, Hyunwoo Kim, Maarten Sap
Abstract: Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems struggle to automatically structure and reason about these implicit social contexts. In this paper, we introduce a novel structured social world representation formalism (S3AP), designed to help AI systems reason more effectively about social dynamics. Following a POMDP-driven design, S3AP represents social interactions as structured tuples, such as state, observation, agent actions, and mental states, which can be automatically induced from free-form narratives or other inputs. We first show S3AP can help LLMs better understand social narratives across 5 social reasoning tasks (e.g., +51% improvement on FANToM's theory-of-mind reasoning with OpenAI's o1), reaching new state-of-the-art (SOTA) performance. We then induce social world models from these structured representations, demonstrating their ability to predict future social dynamics and improve agent decision-making, yielding up to +18% improvement on the SOTOPIA social interaction benchmark. Our findings highlight the promise of S3AP as a powerful, general-purpose representation for social world states, enabling the development of more socially-aware systems that better navigate social interactions.
Comment: Does not match any specific criteria but is tangentially related to embodied AI and reasoning in social contexts. Relevance: 3 Novelty: 7
ArXiv ID: 2509.01238 Authors: Jiasheng Xu, Mingda Li, Yongqiang Tang, Peijie Wang, Wensheng Zhang
Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in language understanding and reasoning. However, their dependence on static training corpora makes them prone to factual errors and knowledge gaps. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge sources, especially structured Knowledge Graphs (KGs), which provide explicit semantics and efficient retrieval. Existing KG-based RAG approaches, however, generally assume that anchor entities are accessible to initiate graph traversal, which limits their robustness in open world settings where accurate linking between the query and the entity is unreliable. To overcome this limitation, we propose AnchorRAG, a novel multi-agent collaboration framework for open-world RAG without the predefined anchor entities. Specifically, a predictor agent dynamically identifies candidate anchor entities by aligning user query terms with KG nodes and initializes independent retriever agents to conduct parallel multi-hop explorations from each candidate. Then a supervisor agent formulates the iterative retrieval strategy for these retriever agents and synthesizes the resulting knowledge paths to generate the final answer. This multi-agent collaboration framework improves retrieval robustness and mitigates the impact of ambiguous or erroneous anchors. Extensive experiments on four public benchmarks demonstrate that AnchorRAG significantly outperforms existing baselines and establishes new state-of-the-art results on the real-world question answering tasks.
Comment: Does not closely match any specific criterion but discusses multi-agent collaboration and retrieval-augmented generation, which might be tangentially related to embodied agents or multimodal learning. Relevance: 4 Novelty: 6
ArXiv ID: 2509.01920 Authors: Yilin Guan, Wenyue Hua, Qingfeng Lan, Sun Fei, Dujian Ding, Devang Acharya, Chi Wang, William Yang Wang
Abstract: Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical deployment challenges due to prohibitive latency and inference costs. While recent work has explored various methods to accelerate inference, existing approaches suffer from significant limitations: they either fail to preserve performance fidelity, require extensive offline training of router modules, or incur excessive operational costs. Moreover, they provide minimal user control over the tradeoff between acceleration and other performance metrics. To address these gaps, we introduce Dynamic Speculative Planning (DSP), an asynchronous online reinforcement learning framework that provides lossless acceleration with substantially reduced costs without requiring additional pre-deployment preparation. DSP explicitly optimizes a joint objective balancing end-to-end latency against dollar cost, allowing practitioners to adjust a single parameter that steers the system toward faster responses, cheaper operation, or any point along this continuum. Experiments on two standard agent benchmarks demonstrate that DSP achieves comparable efficiency to the fastest lossless acceleration method while reducing total cost by 30% and unnecessary cost up to 60%. Our code and data are available through https://github.com/guanyilin428/Dynamic-Speculative-Planning.
Comment: Does not match any specific criteria but is relevant to the general interest area of machine learning and optimization. Relevance: 3 Novelty: 6
ArXiv ID: 2509.01373 Authors: Wei Lu, Lingyu Zhu, Si-Bao Chen
Abstract: Low light conditions significantly degrade Unmanned Aerial Vehicles (UAVs) performance in critical applications. Existing Low-light Image Enhancement (LIE) methods struggle with the unique challenges of aerial imagery, including Ultra-High Resolution (UHR), lack of paired data, severe non-uniform illumination, and deployment constraints. To address these issues, we propose three key contributions. First, we present U3D, the first unsupervised UHR UAV dataset for LIE, with a unified evaluation toolkit. Second, we introduce the Edge Efficiency Index (EEI), a novel metric balancing perceptual quality with key deployment factors: speed, resolution, model complexity, and memory footprint. Third, we develop U3LIE, an efficient framework with two training-only designs-Adaptive Pre-enhancement Augmentation (APA) for input normalization and a Luminance Interval Loss (L_int) for exposure control. U3LIE achieves SOTA results, processing 4K images at 23.8 FPS on a single GPU, making it ideal for real-time on-board deployment. In summary, these contributions provide a holistic solution (dataset, metric, and method) for advancing robust 24/7 UAV vision. The code and datasets are available at https://github.com/lwCVer/U3D_Toolkit.
Comment: Does not match any specific criteria but introduces a benchmark and framework for UAV low-light image enhancement, which is tangentially related to computer vision. Relevance: 3 Novelty: 6
ArXiv ID: 2509.00072 Authors: Terry Jingchen Zhang, Gopal Dev, Ning Wang, Nicole Ni, Wenyuan Jiang, Yinya Huang, Bernhard Sch"olkopf, Mrinmaya Sachan, Zhijing Jin
Abstract: Capability evaluation of large language models (LLMs) is increasingly shadowed by rising concerns of data contamination that cast doubts on whether static benchmarks measure genuine reasoning or mere memorization. We present an empirical study using an infinitely scalable framework to synthesize research-level QA directly from arXiv papers, harnessing the natural temporal structure of research publications where performance decay after knowledge cutoffs may indicate potential contamination. We evaluated 4 frontier model represented by 2 models of different knowledge cutoff dates per family on 1,643 multi-step reasoning questions synthesized from 20,277 arXiv papers stratified over 26 months, covering at least 6 months before and after all cutoff dates. Our results consistently showed a lack of significant performance decay near knowledge cutoff dates for models of various sizes, developers, and release dates. We further performed a comparative analysis with previous longitudinal studies that reported significant post-cutoff performance decay using directly retrieved questions based on public data. we hypothesize that the multi-step reasoning required by our synthesis pipeline offered additional complexity that goes deeper than shallow memorization, which effectively serves a mitigation strategy against benchmark contamination. We fully open source our code and dataset to aid reproducibility and advocate for a paradigm shift that prioritize reasoning-driven synthesis to construct benchmarks over simply collecting newly released questions periodically.
Comment: Does not match any specific criteria but discusses reasoning-driven synthesis for LLM evaluation, which is of general interest. Relevance: 3 Novelty: 6
ArXiv ID: 2509.01469 Authors: Vanessa Sklyarova, Egor Zakharov, Malte Prinzler, Giorgio Becherini, Michael J. Black, Justus Thies
Abstract: We present a novel approach for 3D hair reconstruction from single photographs based on a global hair prior combined with local optimization. Capturing strand-based hair geometry from single photographs is challenging due to the variety and geometric complexity of hairstyles and the lack of ground truth training data. Classical reconstruction methods like multi-view stereo only reconstruct the visible hair strands, missing the inner structure of hairstyles and hampering realistic hair simulation. To address this, existing methods leverage hairstyle priors trained on synthetic data. Such data, however, is limited in both quantity and quality since it requires manual work from skilled artists to model the 3D hairstyles and create near-photorealistic renderings. To address this, we propose a novel approach that uses both, real and synthetic data to learn an effective hairstyle prior. Specifically, we train a transformer-based prior model on synthetic data to obtain knowledge of the internal hairstyle geometry and introduce real data in the learning process to model the outer structure. This training scheme is able to model the visible hair strands depicted in an input image, while preserving the general 3D structure of hairstyles. We exploit this prior to create a Gaussian-splatting-based reconstruction method that creates hairstyles from one or more images. Qualitative and quantitative comparisons with existing reconstruction pipelines demonstrate the effectiveness and superior performance of our method for capturing detailed hair orientation, overall silhouette, and backside consistency. For additional results and code, please refer to https://im2haircut.is.tue.mpg.de.
Comment: Does not match any specific criteria but is related to computer vision and generative modeling, which are of general interest. Relevance: 3 Novelty: 6
ArXiv ID: 2509.00749 Authors: Sangyu Han, Yearim Kim, Nojun Kwak
Abstract: Understanding what sparse auto-encoder (SAE) features in vision transformers truly represent is usually done by inspecting the patches where a feature's activation is highest. However, self-attention mixes information across the entire image, so an activated patch often co-occurs with-but does not cause-the feature's firing. We propose Causal Feature Explanation (CaFE), which leverages Effective Receptive Field (ERF). We consider each activation of an SAE feature to be a target and apply input-attribution methods to identify the image patches that causally drive that activation. Across CLIP-ViT features, ERF maps frequently diverge from naive activation maps, revealing hidden context dependencies (e.g., a "roaring face" feature that requires the co-occurrence of eyes and nose, rather than merely an open mouth). Patch insertion tests confirm that CaFE more effectively recovers or suppresses feature activations than activation-ranked patches. Our results show that CaFE yields more faithful and semantically precise explanations of vision-SAE features, highlighting the risk of misinterpretation when relying solely on activation location.
Comment: Does not match any specific criteria but is related to understanding sparse autoencoder features in vision transformers. Relevance: 3 Novelty: 6
ArXiv ID: 2509.02024 Authors: Nikolaos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki
Abstract: This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synthetic hard negatives but rarely in the context of vision transformers. We build on this observation and integrate synthetic hard negatives to improve vision transformer representation learning. This simple yet effective technique notably improves the discriminative power of learned representations. Our experiments show performance improvements for both DeiT-S and Swin-T architectures.
Comment: Does not match any specific criteria but is related to vision transformers and representation learning. Relevance: 3 Novelty: 6
ArXiv ID: 2509.01544 Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Abstract: Large language models (LLMs) often produce correct answers while relying on flawed or irrelevant reasoning traces, undermining their trustworthiness in high-stakes domains. We propose Counterfactual Sensitivity Regularization (CSR), a lightweight training objective that enforces dependence between intermediate reasoning and final outputs. CSR introduces automated, operator-level counterfactual interventions (e.g., swapping "+" with "-") during training and penalizes models that preserve the same answer under logically invalid traces. This requires only one additional forward pass per sample. To measure faithfulness, we introduce Counterfactual Outcome Sensitivity (COS), which quantifies the impact of such perturbations on model predictions. Across structured reasoning tasks - arithmetic (GSM8K), logical deduction (PrOntoQA), and planning (Blocks World) - CSR improves faithfulness by up to 70 percentage points over standard fine-tuning and process supervision, with only minor accuracy loss. The learned sensitivity generalizes to larger models and synergizes with inference-time methods such as self-consistency. A pilot study on HellaSwag further demonstrates that extending CSR with semantic perturbations can enhance faithfulness in commonsense reasoning.
Comment: Does not closely match any specific criterion but is relevant to reasoning and faithfulness in language models. Relevance: 3 Novelty: 6
ArXiv ID: 2509.00787 Authors: Ganxi Xu, Jinyi Long, Jia Zhang
Abstract: Visual prostheses have shown great potential in restoring vision for blind individuals. On the one hand, researchers have been continuously improving the brain decoding framework of visual prostheses by leveraging the powerful image generation capabilities of diffusion models. On the other hand, the brain encoding stage of visual prostheses struggles to generate brain signals with sufficient biological similarity. Although existing works have recognized this problem, the quality of predicted stimuli still remains a critical issue, as existing approaches typically lack supervised signals from real brain responses to validate the biological plausibility of predicted stimuli. To address this issue, we propose a novel image-to-brain framework based on denoising diffusion probabilistic models (DDPMs) enhanced with cross-attention mechanisms. Our framework consists of two key architectural components: a pre-trained CLIP visual encoder that extracts rich semantic representations from input images, and a cross-attention enhanced U-Net diffusion model that learns to reconstruct biologically plausible brain signals through iterative denoising. Unlike conventional generative models that rely on simple concatenation for conditioning, our cross-attention modules enable dynamic interaction between visual features and brain signal representations, facilitating fine-grained alignment during the generation process. We evaluate our framework on two multimodal datasets (THINGS-EEG2 and THINGS-MEG) to demonstrate its effectiveness in generating biologically plausible brain signals. Moreover, we visualize the training and test M/EEG topographies for all subjects on both datasets to intuitively demonstrate the intra-subject variations and inter-subject variations in M/EEG signals.
Comment: Does not closely match any specific criterion but discusses diffusion-based image-to-brain signal generation, which might be tangentially related to vision foundation models. Relevance: 3 Novelty: 6
ArXiv ID: 2509.00356 Authors: Jin Ye, Fengchao Xiong, Jun Zhou, Yuntao Qian
Abstract: Hyperspectral image (HSI) denoising is a crucial preprocessing step for subsequent tasks. The clean HSI usually reside in a low-dimensional subspace, which can be captured by low-rank and sparse representation, known as the physical prior of HSI. It is generally challenging to adequately use such physical properties for effective denoising while preserving image details. This paper introduces a novel iterative low-rank network (ILRNet) to address these challenges. ILRNet integrates the strengths of model-driven and data-driven approaches by embedding a rank minimization module (RMM) within a U-Net architecture. This module transforms feature maps into the wavelet domain and applies singular value thresholding (SVT) to the low-frequency components during the forward pass, leveraging the spectral low-rankness of HSIs in the feature domain. The parameter, closely related to the hyperparameter of the singular vector thresholding algorithm, is adaptively learned from the data, allowing for flexible and effective capture of low-rankness across different scenarios. Additionally, ILRNet features an iterative refinement process that adaptively combines intermediate denoised HSIs with noisy inputs. This manner ensures progressive enhancement and superior preservation of image details. Experimental results demonstrate that ILRNet achieves state-of-the-art performance in both synthetic and real-world noise removal tasks.
Comment: Does not match any specific criteria but is relevant to the general interest area of computer vision and machine learning. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00872 Authors: Zirui Zhou, Zizhao Peng, Dongyang Jin, Chao Fan, Fengwei An, Shiqi Yu
Abstract: Recent AI-based scoliosis screening methods primarily rely on large-scale silhouette datasets, often neglecting clinically relevant postural asymmetries-key indicators in traditional screening. In contrast, pose data provide an intuitive skeletal representation, enhancing clinical interpretability across various medical applications. However, pose-based scoliosis screening remains underexplored due to two main challenges: (1) the scarcity of large-scale, annotated pose datasets; and (2) the discrete and noise-sensitive nature of raw pose coordinates, which hinders the modeling of subtle asymmetries. To address these limitations, we introduce Scoliosis1K-Pose, a 2D human pose annotation set that extends the original Scoliosis1K dataset, comprising 447,900 frames of 2D keypoints from 1,050 adolescents. Building on this dataset, we introduce the Dual Representation Framework (DRF), which integrates a continuous skeleton map to preserve spatial structure with a discrete Postural Asymmetry Vector (PAV) that encodes clinically relevant asymmetry descriptors. A novel PAV-Guided Attention (PGA) module further uses the PAV as clinical prior to direct feature extraction from the skeleton map, focusing on clinically meaningful asymmetries. Extensive experiments demonstrate that DRF achieves state-of-the-art performance. Visualizations further confirm that the model leverages clinical asymmetry cues to guide feature extraction and promote synergy between its dual representations. The dataset and code are publicly available at https://zhouzi180.github.io/Scoliosis1K/.
Comment: Does not match any specific criteria but involves pose-based learning for medical applications, which is tangentially related to computer vision. Relevance: 3 Novelty: 5
ArXiv ID: 2509.02261 Authors: Yihong Wu, Jinqiao Wei, Xionghui Zhao, Yidi Li, Shaoyi Du, Bin Ren, Nicu Sebe
Abstract: Deep learning-based crowd counting methods have achieved remarkable progress in recent years. However, in complex crowd scenarios, existing models still face challenges when adapting to significant density distribution differences between regions. Additionally, the inconsistency of individual representations caused by viewpoint changes and body posture differences further limits the counting accuracy of the models. To address these challenges, we propose DSGC-Net, a Dual-Stream Graph Convolutional Network based on feature correlation mining. DSGC-Net introduces a Density Approximation (DA) branch and a Representation Approximation (RA) branch. By modeling two semantic graphs, it captures the potential feature correlations in density variations and representation distributions. The DA branch incorporates a density prediction module that generates the density distribution map, and constructs a density-driven semantic graph based on density similarity. The RA branch establishes a representation-driven semantic graph by computing global representation similarity. Then, graph convolutional networks are applied to the two semantic graphs separately to model the latent semantic relationships, which enhance the model's ability to adapt to density variations and improve counting accuracy in multi-view and multi-pose scenarios. Extensive experiments on three widely used datasets demonstrate that DSGC-Net outperforms current state-of-the-art methods. In particular, we achieve MAE of 48.9 and 5.9 in ShanghaiTech Part A and Part B datasets, respectively. The released code is available at: https://github.com/Wu-eon/CrowdCounting-DSGCNet.
Comment: Does not match any specific criteria but is related to computer vision and crowd counting, which are of general interest. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01716 Authors: Rui Zhao, Vladyslav Melnychuk, Jun Zhao, Jesse Wright, Nigel Shadbolt
Abstract: In modern times, people have numerous online accounts, but they rarely read the Terms of Service or Privacy Policy of those sites, despite claiming otherwise, due to the practical difficulty in comprehending them. The mist of data privacy practices forms a major barrier for user-centred Web approaches, and for data sharing and reusing in an agentic world. Existing research proposed methods for using formal languages and reasoning for verifying the compliance of a specified policy, as a potential cure for ignoring privacy policies. However, a critical gap remains in the creation or acquisition of such formal policies at scale. We present a semantic-centric approach for using state-of-the-art large language models (LLM), to automatically identify key information about privacy practices from privacy policies, and construct $\mathit{Pr}^2\mathit{Graph}$, knowledge graph with grounding from Data Privacy Vocabulary (DPV) for privacy practices, to support downstream tasks. Along with the pipeline, the $\mathit{Pr}^2\mathit{Graph}$ for the top-100 popular websites is also released as a public resource, by using the pipeline for analysis. We also demonstrate how the $\mathit{Pr}^2\mathit{Graph}$ can be used to support downstream tasks by constructing formal policy representations such as Open Digital Right Language (ODRL) or perennial semantic Data Terms of Use (psDToU). To evaluate the technology capability, we enriched the Policy-IE dataset by employing legal experts to create custom annotations. We benchmarked the performance of different large language models for our pipeline and verified their capabilities. Overall, they shed light on the possibility of large-scale analysis of online services' privacy practices, as a promising direction to audit the Web and the Internet. We release all datasets and source code as public resources to facilitate reuse and improvement.
Comment: Does not match any specific criteria but involves LLMs and semantic analysis, which are of general interest. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01898 Authors: Zhipeng Weng, Xiaopeng Liu, Ce Liu, Xingyuan Guo, Yukai Shi, Liang Lin
Abstract: Although large scale models achieve significant improvements in performance, the overfitting challenge still frequently undermines their generalization ability. In super resolution tasks on images, diffusion models as representatives of generative models typically adopt large scale architectures. However, few-shot drone-captured infrared training data frequently induces severe overfitting in large-scale architectures. To address this key challenge, our method proposes a new Gaussian quantization representation learning method oriented to diffusion models that alleviates overfitting and enhances robustness. At the same time, an effective monitoring mechanism tracks large scale architectures during training to detect signs of overfitting. By introducing Gaussian quantization representation learning, our method effectively reduces overfitting while maintaining architecture complexity. On this basis, we construct a multi source drone-based infrared image benchmark dataset for detection and use it to emphasize overfitting issues of large scale architectures in few sample, drone-based diverse drone-based image reconstruction scenarios. To verify the efficacy of the method in mitigating overfitting, experiments are conducted on the constructed benchmark. Experimental results demonstrate that our method outperforms existing super resolution approaches and significantly mitigates overfitting of large scale architectures under complex conditions. The code and DroneSR dataset will be available at: https://github.com/wengzp1/GARLSR.
Comment: Does not match any specific criterion but is generally relevant to computer vision and machine learning due to its focus on few-shot thermal image super-resolution. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01619 Authors: Abhinav Kumar, Jaechul Roh, Ali Naseh, Amir Houmansadr, Eugene Bagdasarian
Abstract: AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents could overload content providers. At the same time, web agents can bypass CAPTCHAs and other defenses by mimicking user behavior or flood authentication systems with fake accounts. Yet providers must protect their services and content from denial-of-service attacks and scraping by web agents. In this paper, we design a framework that imposes tunable costs on agents before providing access to resources; we call this Web Agent Throttling. We start by formalizing Throttling Gates as challenges issued to an agent that are asymmetric, scalable, robust, and compatible with any agent. Focusing on a common component -- the language model -- we require the agent to solve reasoning puzzles, thereby incurring excessive token-generation costs. However, we find that using existing puzzles, e.g., coding or math, as throttling gates fails to satisfy our properties. To address this, we introduce rebus-based Reasoning Gates, synthetic text puzzles that require multi-hop reasoning over world knowledge (thereby throttling an agent's model). We design a scalable generation and verification protocol for such reasoning gates. Our framework achieves computational asymmetry, i.e., the response-generation cost is 9.2x higher than the generation cost for SOTA models. We further deploy reasoning gates on a custom website and Model Context Protocol (MCP) servers and evaluate with real-world web agents. Finally, we discuss the limitations and environmental impact of real-world deployment of our framework.
Comment: Does not match any specific criterion but is generally relevant to AI and machine learning due to its focus on throttling web agents using reasoning gates. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00045 Authors: Xiang Li, Chong Zhang, Hongpeng Wang, Shreyank Narayana Gowda, Yushi Li, Xiaobo Jin
Abstract: This work focuses on the high carbon emissions generated by deep learning model training, specifically addressing the core challenge of balancing algorithm performance and energy consumption. It proposes an innovative two-dimensional sustainability evaluation system. Different from the traditional single performance-oriented evaluation paradigm, this study pioneered two quantitative indicators that integrate energy efficiency ratio and accuracy: the sustainable harmonic mean (FMS) integrates accumulated energy consumption and performance parameters through the harmonic mean to reveal the algorithm performance under unit energy consumption; the area under the sustainability curve (ASC) constructs a performance-power consumption curve to characterize the energy efficiency characteristics of the algorithm throughout the cycle. To verify the universality of the indicator system, the study constructed benchmarks in various multimodal tasks, including image classification, segmentation, pose estimation, and batch and online learning. Experiments demonstrate that the system can provide a quantitative basis for evaluating cross-task algorithms and promote the transition of green AI research from theory to practice. Our sustainability evaluation framework code can be found here, providing methodological support for the industry to establish algorithm energy efficiency standards.
Comment: Does not match any specific criterion but is generally relevant to machine learning due to its focus on sustainability considerations for algorithms. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01402 Authors: Emmanouil Nikolakakis, Amine Ouasfi, Julie Digne, Razvan Marinescu
Abstract: We present RibPull, a methodology that utilizes implicit occupancy fields to bridge computational geometry and medical imaging. Implicit 3D representations use continuous functions that handle sparse and noisy data more effectively than discrete methods. While voxel grids are standard for medical imaging, they suffer from resolution limitations, topological information loss, and inefficient handling of sparsity. Coordinate functions preserve complex geometrical information and represent a better solution for sparse data representation, while allowing for further morphological operations. Implicit scene representations enable neural networks to encode entire 3D scenes within their weights. The result is a continuous function that can implicitly compesate for sparse signals and infer further information about the 3D scene by passing any combination of 3D coordinates as input to the model. In this work, we use neural occupancy fields that predict whether a 3D point lies inside or outside an object to represent CT-scanned ribcages. We also apply a Laplacian-based contraction to extract the medial axis of the ribcage, thus demonstrating a geometrical operation that benefits greatly from continuous coordinate-based 3D scene representations versus voxel-based representations. We evaluate our methodology on 20 medical scans from the RibSeg dataset, which is itself an extension of the RibFrac dataset. We will release our code upon publication.
Comment: Does not match any specific criterion but is generally relevant to computer vision and machine learning due to its focus on implicit 3D representations for medical imaging. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00859 Authors: Jiacheng Jiang, Yuan Meng, Chen Tang, Han Yu, Qun Li, Zhi Wang, Wenwu Zhu
Abstract: Current quantization-aware training (QAT) methods primarily focus on enhancing the performance of quantized models on in-distribution (I.D) data, while overlooking the potential performance degradation on out-of-distribution (OOD) data. In this paper, we first substantiate this problem through rigorous experiment, showing that QAT can lead to a significant OOD generalization performance degradation. Further, we find the contradiction between the perspective that flatness of loss landscape gives rise to superior OOD generalization and the phenomenon that QAT lead to a sharp loss landscape, can cause the above problem. Therefore, we propose a flatness-oriented QAT method, FQAT, to achieve generalizable QAT. Specifically, i) FQAT introduces a layer-wise freezing mechanism to mitigate the gradient conflict issue between dual optimization objectives (i.e., vanilla QAT and flatness). ii) FQAT proposes an disorder-guided adaptive freezing algorithm to dynamically determines which layers to freeze at each training step, effectively addressing the challenges caused by interference between layers. A gradient disorder metric is designed to help the algorithm identify unstable layers during training. Extensive experiments on influential OOD benchmark demonstrate the superiority of our method over state-of-the-art baselines under both I.D and OOD image classification tasks.
Comment: Does not closely match any specific criterion but is relevant to the general interest area of machine learning. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00374 Authors: Mengke Li, Lihao Chen, Peng Zhang, Yiu-ming Cheung, Hui Huang
Abstract: Parameter-efficient fine-tuning strategies for foundation models in 1D textual and 2D visual analysis have demonstrated remarkable efficacy. However, due to the scarcity of point cloud data, pre-training large 3D models remains a challenging task. While many efforts have been made to apply pre-trained visual models to 3D domains through "high-to-low" mapping, these approaches often lead to the loss of spatial geometries and lack a generalizable framework for adapting any modality to 3D. This paper, therefore, attempts to directly leverage point features to calibrate the heterogeneous foundation model of any modality for 3D point cloud analysis. Specifically, we propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters, enabling direct point cloud processing without heterogeneous mappings. We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers to ensure seamless utilization of frozen pre-trained models. Given the inherent disorder of point clouds, in contrast to the structured nature of images and language, we employ a permutation-invariant feature to capture the relative positions of point embeddings, thereby obtaining point tokens enriched with location information to optimize self-attention mechanisms. To calibrate self-attention across source domains of any modality to 3D and reduce computational overhead, we introduce a prompt generator that shares weights with the point embedding module, dynamically producing point-prompts without adding additional parameters. These prompts are then concatenated into a frozen foundation model, providing rich global structural information and compensating for the lack of structural context in the heterogeneous data.
Comment: Does not closely match any specific criterion but is relevant to the general interest area of computer vision and machine learning. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01242 Authors: Lee Chae-Yeon, Nam Hyeon-Woo, Tae-Hyun Oh
Abstract: 3D hand pose estimation is a fundamental task in understanding human hands. However, accurately estimating 3D hand poses remains challenging due to the complex movement of hands, self-similarity, and frequent occlusions. In this work, we address two limitations: the inability of existing 3D hand pose estimation methods to estimate aleatoric (data) uncertainty, and the lack of uncertainty modeling that incorporates joint correlation knowledge, which has not been thoroughly investigated. To this end, we introduce aleatoric uncertainty modeling into the 3D hand pose estimation framework, aiming to achieve a better trade-off between modeling joint correlations and computational efficiency. We propose a novel parameterization that leverages a single linear layer to capture intrinsic correlations among hand joints. This is enabled by formulating the hand joint output space as a probabilistic distribution, allowing the linear layer to capture joint correlations. Our proposed parameterization is used as a task head layer, and can be applied as an add-on module on top of the existing models. Our experiments demonstrate that our parameterization for uncertainty modeling outperforms existing approaches. Furthermore, the 3D hand pose estimation model equipped with our uncertainty head achieves favorable accuracy in 3D hand pose estimation while introducing new uncertainty modeling capability to the model. The project page is available at https://hand-uncertainty.github.io/.
Comment: Does not closely match any specific criterion but is relevant to the general interest area of computer vision and machine learning. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00961 Authors: Lun Ai, Johannes Langer, Ute Schmid, Stephen Muggleton
Abstract: Ultra Strong Machine Learning (USML) refers to symbolic learning systems that not only improve their own performance but can also teach their acquired knowledge to quantifiably improve human performance. In this work, we present LENS (Logic Programming Explanation via Neural Summarisation), a neuro-symbolic method that combines symbolic program synthesis with large language models (LLMs) to automate the explanation of machine-learned logic programs in natural language. LENS addresses a key limitation of prior USML approaches by replacing hand-crafted explanation templates with scalable automated generation. Through systematic evaluation using multiple LLM judges and human validation, we demonstrate that LENS generates superior explanations compared to direct LLM prompting and hand-crafted templates. To investigate whether LENS can teach transferable active learning strategies, we carried out a human learning experiment across three related domains. Our results show no significant human performance improvements, suggesting that comprehensive LLM responses may overwhelm users for simpler problems rather than providing learning support. Our work provides a solid foundation for building effective USML systems to support human learning. The source code is available on: https://github.com/lun-ai/LENS.git.
Comment: Does not closely match any specific criterion but is relevant to explainable AI and human learning. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00378 Authors: Shumpei Takezaki, Ryoma Bise, Shinnosuke Matsuo
Abstract: In this study, we propose a novel data augmentation method that introduces the concept of CutMix into the generation process of diffusion models, thereby exploiting both the ability of diffusion models to generate natural and high-resolution images and the characteristic of CutMix, which combines features from two classes to create diverse augmented data. Representative data augmentation methods for combining images from multiple classes include CutMix and MixUp. However, techniques like CutMix often result in unnatural boundaries between the two images due to contextual differences. Therefore, in this study, we propose a method, called NoiseCutMix, to achieve natural, high-resolution image generation featuring the fused characteristics of two classes by partially combining the estimated noise corresponding to two different classes in a diffusion model. In the classification experiments, we verified the effectiveness of the proposed method by comparing it with conventional data augmentation techniques that combine multiple classes, random image generation using Stable Diffusion, and combinations of these methods. Our codes are available at: https://github.com/shumpei-takezaki/NoiseCutMix
Comment: Does not closely match any specific criterion but is relevant to generative modeling and data augmentation. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00428 Authors: Xuechao Zou, Shun Zhang, Xing Fu, Yue Li, Kai Li, Yushe Cao, Congyan Lang, Pin Tao, Junliang Xing
Abstract: Controllable face generation poses critical challenges in generative modeling due to the intricate balance required between semantic controllability and photorealism. While existing approaches struggle with disentangling semantic controls from generation pipelines, we revisit the architectural potential of Diffusion Transformers (DiTs) through the lens of expert specialization. This paper introduces Face-MoGLE, a novel framework featuring: (1) Semantic-decoupled latent modeling through mask-conditioned space factorization, enabling precise attribute manipulation; (2) A mixture of global and local experts that captures holistic structure and region-level semantics for fine-grained controllability; (3) A dynamic gating network producing time-dependent coefficients that evolve with diffusion steps and spatial locations. Face-MoGLE provides a powerful and flexible solution for high-quality, controllable face generation, with strong potential in generative modeling and security applications. Extensive experiments demonstrate its effectiveness in multimodal and monomodal face generation settings and its robust zero-shot generalization capability. Project page is available at https://github.com/XavierJiezou/Face-MoGLE.
Comment: Does not closely match any specific criterion but is relevant to generative modeling and multimodal learning. Relevance: 3 Novelty: 5
ArXiv ID: 2509.02419 Authors: Tao Wang, Zhenxuan Zhang, Yuanbo Zhou, Xinlin Zhang, Yuanbin Chen, Tao Tan, Guang Yang, Tong Tong
Abstract: The effectiveness of convolutional neural networks in medical image segmentation relies on large-scale, high-quality annotations, which are costly and time-consuming to obtain. Even expert-labeled datasets inevitably contain noise arising from subjectivity and coarse delineations, which disrupt feature learning and adversely impact model performance. To address these challenges, this study propose a Geometric-Structural Dual-Guided Network (GSD-Net), which integrates geometric and structural cues to improve robustness against noisy annotations. It incorporates a Geometric Distance-Aware module that dynamically adjusts pixel-level weights using geometric features, thereby strengthening supervision in reliable regions while suppressing noise. A Structure-Guided Label Refinement module further refines labels with structural priors, and a Knowledge Transfer module enriches supervision and improves sensitivity to local details. To comprehensively assess its effectiveness, we evaluated GSD-Net on six publicly available datasets: four containing three types of simulated label noise, and two with multi-expert annotations that reflect real-world subjectivity and labeling inconsistencies. Experimental results demonstrate that GSD-Net achieves state-of-the-art performance under noisy annotations, achieving improvements of 2.52% on Kvasir, 22.76% on Shenzhen, 8.87% on BU-SUC, and 4.59% on BraTS2020 under SR simulated noise. The codes of this study are available at https://github.com/ortonwang/GSD-Net.
Comment: Does not match any specific criteria but focuses on noise-robust medical image segmentation. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01330 Authors: Fuyou Mao, Beining Wu, Yanfeng Jiang, Han Xue, Yan Tang, Hao Zhang
Abstract: Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework that learns voxel-wise distributions while maintaining strong calibration and practical sampling efficiency. PGRD embeds discrete labels as one-hot targets in a continuous space to align segmentation with diffusion modeling. A coarse prior predictor provides step-wise guidance; the diffusion network then learns the residual to the prior, accelerating convergence and improving calibration. A deep diffusion supervision scheme further stabilizes training by supervising intermediate time steps. Evaluated on representative MRI and CT datasets, PGRD achieves higher Dice scores and lower NLL/ECE values than Bayesian, ensemble, Probabilistic U-Net, and vanilla diffusion baselines, while requiring fewer sampling steps to reach strong performance.
Comment: Does not match any specific criteria but focuses on medical image segmentation using diffusion models. Relevance: 3 Novelty: 5
ArXiv ID: 2509.01398 Authors: Cristina Cornelio, Takuya Ito, Ryan Cory-Wright, Sanjeeb Dash, Lior Horesh
Abstract: Artificial intelligence (AI) is transforming the practice of science. Machine learning and large language models (LLMs) can generate hypotheses at a scale and speed far exceeding traditional methods, offering the potential to accelerate discovery across diverse fields. However, the abundance of hypotheses introduces a critical challenge: without scalable and reliable mechanisms for verification, scientific progress risks being hindered rather than being advanced. In this article, we trace the historical development of scientific discovery, examine how AI is reshaping established practices for scientific discovery, and review the principal approaches, ranging from data-driven methods and knowledge-aware neural architectures to symbolic reasoning frameworks and LLM agents. While these systems can uncover patterns and propose candidate laws, their scientific value ultimately depends on rigorous and transparent verification, which we argue must be the cornerstone of AI-assisted discovery.
Comment: Does not match any specific criteria but discusses AI-driven scientific discovery and verification. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00481 Authors: Anton Wolter, Georgios Vidalakis, Michael Yu, Ankit Grover, Vaishali Dhanoa
Abstract: Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization field, multi-agent systems can be useful for employing agents throughout the entire data-to-communication pipeline. We present a lightweight multi-agent system that automates the data analysis workflow, from data exploration to generating coherent visual narratives for insight communication. Our approach combines a hybrid multi-agent architecture with deterministic components, strategically externalizing critical logic from LLMs to improve transparency and reliability. The system delivers granular, modular outputs that enable surgical modifications without full regeneration, supporting sustainable human-AI collaboration. We evaluated our system across 4 diverse datasets, demonstrating strong generalizability, narrative quality, and computational efficiency with minimal dependencies.
Comment: Does not closely match any specific criterion but discusses multi-agent systems for data visualization and narrative generation, which might be tangentially related to embodied agents. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00658 Authors: Yumeng Lin, Dong Li, Xintao Wu, Minglai Shao, Xujiang Zhao, Zhong Chen, Chen Zhao
Abstract: Ensuring fairness and robustness in machine learning models remains a challenge, particularly under domain shifts. We present Face4FairShifts, a large-scale facial image benchmark designed to systematically evaluate fairness-aware learning and domain generalization. The dataset includes 100,000 images across four visually distinct domains with 39 annotations within 14 attributes covering demographic and facial features. Through extensive experiments, we analyze model performance under distribution shifts and identify significant gaps. Our findings emphasize the limitations of existing related datasets and the need for more effective fairness-aware domain adaptation techniques. Face4FairShifts provides a comprehensive testbed for advancing equitable and reliable AI systems. The dataset is available online at https://meviuslab.github.io/Face4FairShifts/.
Comment: Does not closely match any specific criterion but introduces a fairness-focused benchmark for visual domains, which might be tangentially related to vision foundation models. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00997 Authors: Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito, Shuo Yuan, Ion Stoica, Matei Zaharia, Alvin Cheung, Natacha Crooks, Joseph E. Gonzalez, Aditya G. Parameswaran
Abstract: Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of exploration and solution formulation for the given task, one we call agentic speculation. The sheer volume and inefficiencies of agentic speculation can pose challenges for present-day data systems. We argue that data systems need to adapt to more natively support agentic workloads. We take advantage of the characteristics of agentic speculation that we identify, i.e., scale, heterogeneity, redundancy, and steerability - to outline a number of new research opportunities for a new agent-first data systems architecture, ranging from new query interfaces, to new query processing techniques, to new agentic memory stores.
Comment: Does not closely match any specific criterion but discusses agentic workloads and data systems, which might be tangentially related to embodied agents. Relevance: 3 Novelty: 5
ArXiv ID: 2509.00781 Authors: Haomiao Tang, Wenjie Li, Yixiang Qiu, Genping Wang, Shu-Tao Xia
Abstract: Despite the ubiquity of modern face retrieval systems, their retrieval stage is often outsourced to third-party entities, posing significant risks to user portrait privacy. Although homomorphic encryption (HE) offers strong security guarantees by enabling arithmetic computations in the cipher space, its high computational inefficiency makes it unsuitable for real-time, real-world applications. To address this issue, we propose Cancelable Product Quantization, a highly efficient framework for secure face representation retrieval. Our hierarchical two-stage framework comprises: (i) a high-throughput cancelable PQ indexing module for fast candidate filtering, and (ii) a fine-grained cipher-space retrieval module for final precise face ranking. A tailored protection mechanism is designed to secure the indexing module for cancelable biometric authentication while ensuring efficiency. Experiments on benchmark datasets demonstrate that our method achieves an decent balance between effectiveness, efficiency and security.
Comment: Does not match any specific criterion but is generally relevant to computer vision and machine learning due to its focus on secure and scalable face retrieval. Relevance: 3 Novelty: 4
ArXiv ID: 2509.02451 Authors: Rangel Daroya, Taylor Rowley, Jonathan Flores, Elisa Friedmann, Fiona Bennitt, Heejin An, Travis Simmons, Marissa Jean Hughes, Camryn L Kluetmeier, Solomon Kica, J. Daniel V'elez, Sarah E. Esenther, Thomas E. Howard, Yanqi Ye, Audrey Turcotte, Colin Gleason, Subhransu Maji
Abstract: Surface water dynamics play a critical role in Earth's climate system, influencing ecosystems, agriculture, disaster resilience, and sustainable development. Yet monitoring rivers and surface water at fine spatial and temporal scales remains challenging -- especially for narrow or sediment-rich rivers that are poorly captured by low-resolution satellite data. To address this, we introduce RiverScope, a high-resolution dataset developed through collaboration between computer science and hydrology experts. RiverScope comprises 1,145 high-resolution images (covering 2,577 square kilometers) with expert-labeled river and surface water masks, requiring over 100 hours of manual annotation. Each image is co-registered with Sentinel-2, SWOT, and the SWOT River Database (SWORD), enabling the evaluation of cost-accuracy trade-offs across sensors -- a key consideration for operational water monitoring. We also establish the first global, high-resolution benchmark for river width estimation, achieving a median error of 7.2 meters -- significantly outperforming existing satellite-derived methods. We extensively evaluate deep networks across multiple architectures (e.g., CNNs and transformers), pretraining strategies (e.g., supervised and self-supervised), and training datasets (e.g., ImageNet and satellite imagery). Our best-performing models combine the benefits of transfer learning with the use of all the multispectral PlanetScope channels via learned adaptors. RiverScope provides a valuable resource for fine-scale and multi-sensor hydrological modeling, supporting climate adaptation and sustainable water management.
Comment: Does not match any specific criterion but is generally relevant to computer vision and machine learning due to its introduction of a high-resolution river masking dataset. Relevance: 3 Novelty: 4
ArXiv ID: 2509.00757 Authors: Xiufeng Huang, Ziyuan Luo, Qi Song, Ruofei Wang, Renjie Wan
Abstract: The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive fine-tuning procedures for each predefined message. We propose the first generalizable watermarking framework that enables efficient protection of Splatter Image-based 3DGS models through a single forward pass. We introduce GaussianBridge that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding. To ensure imperceptibility, we design a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality. For robust message recovery, we develop a dense segmentation-based extraction mechanism that maintains reliable extraction even when watermarked objects occupy minimal regions in rendered views. Project page: https://kevinhuangxf.github.io/marksplatter.
Comment: Does not closely match any specific criterion but is relevant to 3D modeling and watermarking. Relevance: 3 Novelty: 4
In suggesting papers to your friend, remember that he enjoys papers on computer vision and machine learning, and generative modeling in multi-modal learning. Your friend also likes learning about surprising empirical or insightful results in vision-language models or embodied AI, as well as clever statistical tricks.