Total relevant papers: 49
Paper selection prompt and criteria at the bottom
Table of contents with paper titles:
Spatial Mental Modeling from Limited Views Authors: Baiqiao Yin, Qineng Wang, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Manling Li, Jiajun Wu, Li Fei-Fei
Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration Authors: Jiahe Chen, Jiaying He, Qian Shao, Qiyuan Chen, Jiahe Ying, Hongxia Xu, Jintai Chen, Jianwei Zheng, Jian Wu
Out-of-Distribution Semantic Occupancy Prediction Authors: Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Ruiping Liu, Fei Teng, Kai Luo, Zhiyong Li, Kailun Yang
Global and Local Entailment Learning for Natural World Imagery Authors: Srikumar Sastry, Aayush Dhakal, Eric Xing, Subash Khanal, Nathan Jacobs
DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion Authors: Yansong Qu, Shaohui Dai, Xinyang Li, Yuze Wang, You Shen, Liujuan Cao, Rongrong Ji
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition Authors: Longkun Zou, Kangjun Liu, Ke Chen, Kailing Guo, Kui Jia, Yaowei Wang
Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation Authors: Ze Wang, Hao Chen, Benran Hu, Jiang Liu, Ximeng Sun, Jialian Wu, Yusheng Su, Xiaodong Yu, Emad Barsoum, Zicheng Liu
DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing Authors: Lingling Cai, Kang Zhao, Hangjie Yuan, Xiang Wang, Yingya Zhang, Kejie Huang
DidSee: Diffusion-Based Depth Completion for Material-Agnostic Robotic Perception and Manipulation Authors: Wenzhou Lyu, Jialing Lin, Wenqi Ren, Ruihao Xia, Feng Qian, Yang Tang
DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting Authors: Yeon-Ji Song, Jaein Kim, Byung-Ju Kim, Byoung-Tak Zhang
HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation Authors: Diego Biagini, Nassir Navab, Azade Farshad
DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation Authors: Umaima Rahman, Mohammad Yaqub, Dwarikanath Mahapatra
Rethink Sparse Signals for Pose-guided Text-to-image Generation Authors: Wenjie Xuan, Jing Zhang, Juhua Liu, Bo Du, Dacheng Tao
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection Authors: Zhixin Cheng, Jiacheng Deng, Xinjun Li, Xiaotian Yin, Bohao Liao, Baoqun Yin, Wenfei Yang, Tianzhu Zhang
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation Authors: Bowen Chen, Mengyi Zhao, Haomiao Sun, Li Chen, Xu Wang, Kang Du, Xinglong Wu
HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context Authors: Qize Yang, Shimin Yao, Weixuan Chen, Shenghao Fu, Detao Bai, Jiaxing Zhao, Boyuan Sun, Bowen Yin, Xihan Wei, Jingren Zhou
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans Authors: Shubhankar Borse, Seokeon Choi, Sunghyun Park, Jeongho Kim, Shreya Kadambi, Risheek Garrepalli, Sungrack Yun, Munawar Hayat, Fatih Porikli
Task-Aware KV Compression For Cost-Effective Long Video Understanding Authors: Minghao Qin, Yan Shu, Peitian Zhang, Kun Lun, Huaying Yuan, Juenjie Zhou, Shitao Xiao, Bo Zhao, Zheng Liu
ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models Authors: Hongbo Liu, Jingwen He, Yi Jin, Dian Zheng, Yuhao Dong, Fan Zhang, Ziqi Huang, Yinan He, Yangguang Li, Weichao Chen, Yu Qiao, Wanli Ouyang, Shengjie Zhao, Ziwei Liu
DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images Authors: Badri Vishal Kasuba, Parag Chaudhuri, Ganesh Ramakrishnan
GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding Authors: Zijun Lin, Shuting He, Cheston Tan, Bihan Wen
Ad-Hoc Human-AI Coordination Challenge Authors: Tin Dizdarevi'c, Ravi Hammond, Tobias Gessler, Anisoara Calinescu, Jonathan Cook, Matteo Gallici, Andrei Lupu, Jakob Nicolaus Foerster
EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception Authors: Sanjoy Chowdhury, Subrata Biswas, Sayan Nag, Tushar Nagarajan, Calvin Murdock, Ishwarya Ananthabhotla, Yijun Qian, Vamsi Krishna Ithapu, Dinesh Manocha, Ruohan Gao
TSDASeg: A Two-Stage Model with Direct Alignment for Interactive Point Cloud Segmentation Authors: Chade Li, Pengju Zhang, Yihong Wu
OmniEval: A Benchmark for Evaluating Omni-modal Models with Visual, Auditory, and Textual Inputs Authors: Yiman Zhang, Ziheng Luo, Qiangyu Yan, Wei He, Borui Jiang, Xinghao Chen, Kai Han
TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding Authors: Junwen Zhang, Pu Chen, Yin Zhang
StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation Authors: Haodong Li, Chen Wang, Jiahui Lei, Kostas Daniilidis, Lingjie Liu
G$^{2}$D: Boosting Multimodal Learning with Gradient-Guided Distillation Authors: Mohammed Rakib, Arunkumar Bagavathi
SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmark Authors: Alex Costanzino, Pierluigi Zama Ramirez, Luigi Lella, Matteo Ragaglia, Alessandro Oliva, Giuseppe Lisanti, Luigi Di Stefano
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge Authors: Boyu Gou, Zanming Huang, Yuting Ning, Yu Gu, Michael Lin, Weijian Qi, Andrei Kopanev, Botao Yu, Bernal Jim'enez Guti'errez, Yiheng Shu, Chan Hee Song, Jiaman Wu, Shijie Chen, Hanane Nour Moussa, Tianshu Zhang, Jian Xie, Yifei Li, Tianci Xue, Zeyi Liao, Kai Zhang, Boyuan Zheng, Zhaowei Cai, Viktor Rozgic, Morteza Ziyadi, Huan Sun, Yu Su
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation Authors: Xiwei Xuan, Ziquan Deng, Kwan-Liu Ma
PanSt3R: Multi-view Consistent Panoptic Segmentation Authors: Lojze Zust, Yohann Cabon, Juliette Marrie, Leonid Antsfeld, Boris Chidlovskii, Jerome Revaud, Gabriela Csurka
Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation Authors: Sweta Banerjee, Viktoria Weiss, Taryn A. Donovan, Rutger A. Fick, Thomas Conrad, Jonas Ammeling, Nils Porsche, Robert Klopfleisch, Christopher Kaltenecker, Katharina Breininger, Marc Aubreville, Christof A. Bertram
Active Inference AI Systems for Scientific Discovery Authors: Karthik Duraisamy
Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction Authors: Zhirui Gao. Renjiao Yi, Yaqiao Dai, Xuening Zhu, Wei Chen, Chenyang Zhu, Kai Xu
PoseMaster: Generating 3D Characters in Arbitrary Poses from a Single Image Authors: Hongyu Yan, Kunming Luo, Weiyu Li, Yixun Liang, Shengming Li, Jingwei Huang, Chunchao Guo, Ping Tan
GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation Authors: Wentao Hu, Shunkai Li, Ziqiao Peng, Haoxian Zhang, Fan Shi, Xiaoqiang Liu, Pengfei Wan, Di Zhang, Hui Tian
Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation Authors: Ryosuke Kawamura, Hideaki Hayashi, Shunsuke Otake, Noriko Takemura, Hajime Nagahara
The Role of Cyclopean-Eye in Stereo Vision Authors: Sherlon Almeida da Silva, Davi Geiger, Luiz Velho, Moacir Antonelli Ponti
FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization Authors: Ha Min Son, Shahbaz Rezaei, Xin Liu
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? Authors: Haoang Chi, He Li, Wenjing Yang, Feng Liu, Long Lan, Xiaoguang Ren, Tongliang Liu, Bo Han
Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Authors: Chenkai Sun, Denghui Zhang, ChengXiang Zhai, Heng Ji
Learning to See in the Extremely Dark Authors: Hai Jiang, Binhao Guan, Zhen Liu, Xiaohong Liu, Jian Yu, Zheng Liu, Songchen Han, Shuaicheng Liu
From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging Authors: Tao Liu, Dafeng Zhang, Gengchen Li, Shizhuo Liu, Yongqi Song, Senmao Li, Shiqi Yang, Boqian Li, Kai Wang, Yaxing Wang
FedSC: Federated Learning with Semantic-Aware Collaboration Authors: Huan Wang, Haoran Li, Huaming Chen, Jun Yan, Jiahua Shi, Jun Shen
Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency Authors: Kaiyu Song, Hanjiang Lai
Tree-based Semantic Losses: Application to Sparsely-supervised Large Multi-class Hyperspectral Segmentation Authors: Junwen Wang, Oscar Maccormac, William Rochford, Aaron Kujawa, Jonathan Shapey, Tom Vercauteren
MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation Authors: Gurusha Juneja, Alon Albalak, Wenyue Hua, William Yang Wang
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching Authors: Mahmoud Tahmasebi, Saif Huq, Kevin Meehan, Marion McAfee
ArXiv ID: 2506.21458 Authors: Baiqiao Yin, Qineng Wang, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Manling Li, Jiajun Wu, Li Fei-Fei
Abstract: Can Vision Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models, internal representations of unseen space, to reason about layout, perspective, and motion. Our new MindCube benchmark with 21,154 questions across 3,268 images exposes this critical gap, where existing VLMs exhibit near-random performance. Using MindCube, we systematically evaluate how well VLMs build robust spatial mental models through representing positions (cognitive mapping), orientations (perspective-taking), and dynamics (mental simulation for "what-if" movements). We then explore three approaches to help VLMs approximate spatial mental models, including unseen intermediate views, natural language reasoning chains, and cognitive maps. The significant improvement comes from a synergistic approach, "map-then-reason", that jointly trains the model to first generate a cognitive map and then reason upon it. By training models to reason over these internal maps, we boosted accuracy from 37.8% to 60.8% (+23.0%). Adding reinforcement learning pushed performance even further to 70.7% (+32.9%). Our key insight is that such scaffolding of spatial mental models, actively constructing and utilizing internal structured spatial representations with flexible reasoning processes, significantly improves understanding of unobservable space.
Comment: Matches criterion 1 as it explores spatial reasoning and mental modeling for vision-language models. Relevance: 10 Novelty: 8
ArXiv ID: 2506.21509 Authors: Jiahe Chen, Jiaying He, Qian Shao, Qiyuan Chen, Jiahe Ying, Hongxia Xu, Jintai Chen, Jianwei Zheng, Jian Wu
Abstract: Large Vision-Language Models (LVLMs) have demonstrated significant advancements in multimodal understanding, yet they are frequently hampered by hallucination-the generation of text that contradicts visual input. Existing training-free decoding strategies exhibit critical limitations, including the use of static constraints that do not adapt to semantic drift during generation, inefficiency stemming from the need for multiple forward passes, and degradation of detail due to overly rigid intervention rules. To overcome these challenges, this paper introduces Dynamic Logits Calibration (DLC), a novel training-free decoding framework designed to dynamically align text generation with visual evidence at inference time. At the decoding phase, DLC step-wise employs CLIP to assess the semantic alignment between the input image and the generated text sequence. Then, the Relative Visual Advantage (RVA) of candidate tokens is evaluated against a dynamically updated contextual baseline, adaptively adjusting output logits to favor tokens that are visually grounded. Furthermore, an adaptive weighting mechanism, informed by a real-time context alignment score, carefully balances the visual guidance while ensuring the overall quality of the textual output. Extensive experiments conducted across diverse benchmarks and various LVLM architectures (such as LLaVA, InstructBLIP, and MiniGPT-4) demonstrate that DLC significantly reduces hallucinations, outperforming current methods while maintaining high inference efficiency by avoiding multiple forward passes. Overall, we present an effective and efficient decoding-time solution to mitigate hallucinations, thereby enhancing the reliability of LVLMs for more practices. Code will be released on Github.
Comment: Matches criterion 2 as it addresses hallucination in large vision-language models. Relevance: 9 Novelty: 7
ArXiv ID: 2506.21185 Authors: Yuheng Zhang, Mengfei Duan, Kunyu Peng, Yuhang Wang, Ruiping Liu, Fei Teng, Kai Luo, Zhiyong Li, Kailun Yang
Abstract: 3D Semantic Occupancy Prediction is crucial for autonomous driving, providing a dense, semantically rich environmental representation. However, existing methods focus on in-distribution scenes, making them susceptible to Out-of-Distribution (OoD) objects and long-tail distributions, which increases the risk of undetected anomalies and misinterpretations, posing safety hazards. To address these challenges, we introduce Out-of-Distribution Semantic Occupancy Prediction, targeting OoD detection in 3D voxel space. To fill the gaps in the dataset, we propose a Synthetic Anomaly Integration Pipeline that injects synthetic anomalies while preserving realistic spatial and occlusion patterns, enabling the creation of two datasets: VAA-KITTI and VAA-KITTI-360. We introduce OccOoD, a novel framework integrating OoD detection into 3D semantic occupancy prediction, with Voxel-BEV Progressive Fusion (VBPF) leveraging an RWKV-based branch to enhance OoD detection via geometry-semantic fusion. Experimental results demonstrate that OccOoD achieves state-of-the-art OoD detection with an AuROC of 67.34% and an AuPRCr of 29.21% within a 1.2m region, while maintaining competitive occupancy prediction performance. The established datasets and source code will be made publicly available at https://github.com/7uHeng/OccOoD.
Comment: Matches criterion 3 as it introduces a novel framework and datasets for semantic occupancy prediction in 3D space. Relevance: 8 Novelty: 7
ArXiv ID: 2506.21476 Authors: Srikumar Sastry, Aayush Dhakal, Eric Xing, Subash Khanal, Nathan Jacobs
Abstract: Learning the hierarchical structure of data in vision-language models is a significant challenge. Previous works have attempted to address this challenge by employing entailment learning. However, these approaches fail to model the transitive nature of entailment explicitly, which establishes the relationship between order and semantics within a representation space. In this work, we introduce Radial Cross-Modal Embeddings (RCME), a framework that enables the explicit modeling of transitivity-enforced entailment. Our proposed framework optimizes for the partial order of concepts within vision-language models. By leveraging our framework, we develop a hierarchical vision-language foundation model capable of representing the hierarchy in the Tree of Life. Our experiments on hierarchical species classification and hierarchical retrieval tasks demonstrate the enhanced performance of our models compared to the existing state-of-the-art models. Our code and models are open-sourced at https://vishu26.github.io/RCME/index.html.
Comment: Matches criterion 2 as it explores hierarchical vision-language foundation models and their applications. Relevance: 8 Novelty: 7
ArXiv ID: 2506.21544 Authors: Yansong Qu, Shaohui Dai, Xinyang Li, Yuze Wang, You Shen, Liujuan Cao, Rongrong Ji
Abstract: Reconstructing 3D objects from a single image is a long-standing challenge, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they generally assume fully visible inputs and fail when parts of the object are occluded. This leads to inconsistent views and degraded 3D reconstruction quality. To overcome this limitation, we propose an end-to-end framework for occlusion-aware multi-view generation. Our method directly synthesizes six structurally consistent novel views from a single partially occluded image, enabling downstream 3D reconstruction without requiring prior inpainting or manual annotations. We construct a self-supervised training pipeline using the Pix2Gestalt dataset, leveraging occluded-unoccluded image pairs and pseudo-ground-truth views to teach the model structure-aware completion and view consistency. Without modifying the original architecture, we fully fine-tune the view synthesis model to jointly learn completion and multi-view generation. Additionally, we introduce the first benchmark for occlusion-aware reconstruction, encompassing diverse occlusion levels, object categories, and mask patterns. This benchmark provides a standardized protocol for evaluating future methods under partial occlusions. Our code is available at https://github.com/Quyans/DeOcc123.
Comment: Matches criterion 4 as it focuses on 3D reconstruction and novel methodologies in vision foundation models. Relevance: 7 Novelty: 6
ArXiv ID: 2506.21165 Authors: Longkun Zou, Kangjun Liu, Ke Chen, Kailing Guo, Kui Jia, Yaowei Wang
Abstract: Learning semantic representations from point sets of 3D object shapes is often challenged by significant geometric variations, primarily due to differences in data acquisition methods. Typically, training data is generated using point simulators, while testing data is collected with distinct 3D sensors, leading to a simulation-to-reality (Sim2Real) domain gap that limits the generalization ability of point classifiers. Current unsupervised domain adaptation (UDA) techniques struggle with this gap, as they often lack robust, domain-insensitive descriptors capable of capturing global topological information, resulting in overfitting to the limited semantic patterns of the source domain. To address this issue, we introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds. Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures, and by modeling the topological relations of local geometric features through a novel self-supervised learning task. Additionally, we propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training, effectively reducing the impact of noisy pseudo-labels and enhancing the robustness of the adaptation process. Experimental results on three public Sim2Real benchmarks validate the effectiveness of our TAM framework, showing consistent improvements over state-of-the-art methods across all evaluated tasks. The source code of this work will be available at https://github.com/zou-longkun/TAG.git.
Comment: Matches criteria 3 (Embodied/Robotic AI: New Benchmarks or Methods) as it introduces a novel framework for unsupervised simulation-to-reality point cloud recognition. Relevance: 6 Novelty: 7
ArXiv ID: 2506.21022 Authors: Ze Wang, Hao Chen, Benran Hu, Jiang Liu, Ximeng Sun, Jialian Wu, Yusheng Su, Xiaodong Yu, Emad Barsoum, Zicheng Liu
Abstract: Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent spaces have reduced the number of tokens required by eliminating the need for a 2D grid structure. In this paper, we further advance compact discrete image representation by introducing 1D binary image latents. By representing each image as a sequence of binary vectors, rather than using traditional one-hot codebook tokens, our approach preserves high-resolution details while maintaining the compactness of 1D latents. To the best of our knowledge, our text-to-image models are the first to achieve competitive performance in both diffusion and auto-regressive generation using just 128 discrete tokens for images up to 1024x1024, demonstrating up to a 32-fold reduction in token numbers compared to standard VQ-VAEs. The proposed 1D binary latent space, coupled with simple model architectures, achieves marked improvements in speed training and inference speed. Our text-to-image models allow for a global batch size of 4096 on a single GPU node with 8 AMD MI300X GPUs, and the training can be completed within 200 GPU days. Our models achieve competitive performance compared to modern image generation models without any in-house private training data or post-training refinements, offering a scalable and efficient alternative to conventional tokenization methods.
Comment: Matches criteria 2 (Visual and Multimodal Large Language Models) as it explores efficient image tokenization for multimodal understanding and generation. Relevance: 5 Novelty: 8
ArXiv ID: 2506.20967 Authors: Lingling Cai, Kang Zhao, Hangjie Yuan, Xiang Wang, Yingya Zhang, Kejie Huang
Abstract: The advent of Video Diffusion Transformers (Video DiTs) marks a milestone in video generation. However, directly applying existing video editing methods to Video DiTs often incurs substantial computational overhead, due to resource-intensive attention modification or finetuning. To alleviate this problem, we present DFVEdit, an efficient zero-shot video editing method tailored for Video DiTs. DFVEdit eliminates the need for both attention modification and fine-tuning by directly operating on clean latents via flow transformation. To be more specific, we observe that editing and sampling can be unified under the continuous flow perspective. Building upon this foundation, we propose the Conditional Delta Flow Vector (CDFV) -- a theoretically unbiased estimation of DFV -- and integrate Implicit Cross Attention (ICA) guidance as well as Embedding Reinforcement (ER) to further enhance editing quality. DFVEdit excels in practical efficiency, offering at least 20x inference speed-up and 85% memory reduction on Video DiTs compared to attention-engineering-based editing methods. Extensive quantitative and qualitative experiments demonstrate that DFVEdit can be seamlessly applied to popular Video DiTs (e.g., CogVideoX and Wan2.1), attaining state-of-the-art performance on structural fidelity, spatial-temporal consistency, and editing quality.
Comment: Matches criteria 6 (Video Understanding) as it focuses on video editing and generation using Video Diffusion Transformers. Relevance: 6 Novelty: 7
ArXiv ID: 2506.21034 Authors: Wenzhou Lyu, Jialing Lin, Wenqi Ren, Ruihao Xia, Feng Qian, Yang Tang
Abstract: Commercial RGB-D cameras often produce noisy, incomplete depth maps for non-Lambertian objects. Traditional depth completion methods struggle to generalize due to the limited diversity and scale of training data. Recent advances exploit visual priors from pre-trained text-to-image diffusion models to enhance generalization in dense prediction tasks. However, we find that biases arising from training-inference mismatches in the vanilla diffusion framework significantly impair depth completion performance. Additionally, the lack of distinct visual features in non-Lambertian regions further hinders precise prediction. To address these issues, we propose \textbf{DidSee}, a diffusion-based framework for depth completion on non-Lambertian objects. First, we integrate a rescaled noise scheduler enforcing a zero terminal signal-to-noise ratio to eliminate signal leakage bias. Second, we devise a noise-agnostic single-step training formulation to alleviate error accumulation caused by exposure bias and optimize the model with a task-specific loss. Finally, we incorporate a semantic enhancer that enables joint depth completion and semantic segmentation, distinguishing objects from backgrounds and yielding precise, fine-grained depth maps. DidSee achieves state-of-the-art performance on multiple benchmarks, demonstrates robust real-world generalization, and effectively improves downstream tasks such as category-level pose estimation and robotic grasping.Project page: https://wenzhoulyu.github.io/DidSee/
Comment: Matches criterion 3 as it proposes a novel method for depth completion in robotic perception, which is relevant to embodied/robotic AI. Relevance: 5 Novelty: 7
ArXiv ID: 2506.20998 Authors: Yeon-Ji Song, Jaein Kim, Byung-Ju Kim, Byoung-Tak Zhang
Abstract: Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Existing novel view synthesis methods are often constrained by their reliance on high-resolution images or strong assumptions about static geometry and rigid scene priors. Consequently, their approaches lack robustness in real-world environments with dynamic object and camera motion, leading to instability and degraded visual fidelity. To address this, we propose Motion-aware Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting (DBMovi-GS), a method designed for dynamic view synthesis from blurry monocular videos. Our model generates dense 3D Gaussians, restoring sharpness from blurry videos and reconstructing detailed 3D geometry of the scene affected by dynamic motion variations. Our model achieves robust performance in novel view synthesis under dynamic blurry scenes and sets a new benchmark in realistic novel view synthesis for blurry monocular video inputs.
Comment: Matches criterion 6 as it addresses dynamic view synthesis from blurry monocular videos, a novel video understanding task. Relevance: 5 Novelty: 7
ArXiv ID: 2506.21287 Authors: Diego Biagini, Nassir Navab, Azade Farshad
Abstract: Surgical Video Synthesis has emerged as a promising research direction following the success of diffusion models in general-domain video generation. Although existing approaches achieve high-quality video generation, most are unconditional and fail to maintain consistency with surgical actions and phases, lacking the surgical understanding and fine-grained guidance necessary for factual simulation. We address these challenges by proposing HieraSurg, a hierarchy-aware surgical video generation framework consisting of two specialized diffusion models. Given a surgical phase and an initial frame, HieraSurg first predicts future coarse-grained semantic changes through a segmentation prediction model. The final video is then generated by a second-stage model that augments these temporal segmentation maps with fine-grained visual features, leading to effective texture rendering and integration of semantic information in the video space. Our approach leverages surgical information at multiple levels of abstraction, including surgical phase, action triplets, and panoptic segmentation maps. The experimental results on Cholecystectomy Surgical Video Generation demonstrate that the model significantly outperforms prior work both quantitatively and qualitatively, showing strong generalization capabilities and the ability to generate higher frame-rate videos. The model exhibits particularly fine-grained adherence when provided with existing segmentation maps, suggesting its potential for practical surgical applications.
Comment: Matches criterion 6 as it focuses on video understanding and generation in a surgical context. Relevance: 6 Novelty: 6
ArXiv ID: 2506.21237 Authors: Umaima Rahman, Mohammad Yaqub, Dwarikanath Mahapatra
Abstract: We introduce DiMPLe (Disentangled Multi-Modal Prompt Learning), a novel approach to disentangle invariant and spurious features across vision and language modalities in multi-modal learning. Spurious correlations in visual data often hinder out-of-distribution (OOD) performance. Unlike prior methods focusing solely on image features, DiMPLe disentangles features within and across modalities while maintaining consistent alignment, enabling better generalization to novel classes and robustness to distribution shifts. Our method combines three key objectives: (1) mutual information minimization between invariant and spurious features, (2) spurious feature regularization, and (3) contrastive learning on invariant features. Extensive experiments demonstrate DiMPLe demonstrates superior performance compared to CoOp-OOD, when averaged across 11 diverse datasets, and achieves absolute gains of 15.27 in base class accuracy and 44.31 in novel class accuracy.
Comment: Matches criteria 2 (Visual and Multimodal Large Language Models) as it introduces a disentangled multi-modal prompt learning framework for vision and language modalities. Relevance: 5 Novelty: 7
ArXiv ID: 2506.20983 Authors: Wenjie Xuan, Jing Zhang, Juhua Liu, Bo Du, Dacheng Tao
Abstract: Recent works favored dense signals (e.g., depth, DensePose), as an alternative to sparse signals (e.g., OpenPose), to provide detailed spatial guidance for pose-guided text-to-image generation. However, dense representations raised new challenges, including editing difficulties and potential inconsistencies with textual prompts. This fact motivates us to revisit sparse signals for pose guidance, owing to their simplicity and shape-agnostic nature, which remains underexplored. This paper proposes a novel Spatial-Pose ControlNet(SP-Ctrl), equipping sparse signals with robust controllability for pose-guided image generation. Specifically, we extend OpenPose to a learnable spatial representation, making keypoint embeddings discriminative and expressive. Additionally, we introduce keypoint concept learning, which encourages keypoint tokens to attend to the spatial positions of each keypoint, thus improving pose alignment. Experiments on animal- and human-centric image generation tasks demonstrate that our method outperforms recent spatially controllable T2I generation approaches under sparse-pose guidance and even matches the performance of dense signal-based methods. Moreover, SP-Ctrl shows promising capabilities in diverse and cross-species generation through sparse signals. Codes will be available at https://github.com/DREAMXFAR/SP-Ctrl.
Comment: Matches criteria 5 (Integration of Image/Video and Large Language Models) as it focuses on pose-guided text-to-image generation with sparse signals. Relevance: 5 Novelty: 7
ArXiv ID: 2506.21364 Authors: Zhixin Cheng, Jiacheng Deng, Xinjun Li, Xiaotian Yin, Bohao Liao, Baoqun Yin, Wenfei Yang, Tianzhu Zhang
Abstract: Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point correspondences. However, differences in feature channel attention between images and point clouds may lead to degraded matching results, ultimately impairing registration accuracy. Furthermore, similar structures in the scene could lead to redundant correspondences in cross-modal matching. To address these issues, we propose Channel Adaptive Adjustment Module (CAA) and Global Optimal Selection Module (GOS). CAA enhances intra-modal features and suppresses cross-modal sensitivity, while GOS replaces local selection with global optimization. Experiments on RGB-D Scenes V2 and 7-Scenes demonstrate the superiority of our method, achieving state-of-the-art performance in image-to-point cloud registration.
Comment: Matches criteria 1 (Spatial Intelligence and Embodied Agents) as it addresses spatial reasoning in image-to-point cloud registration. Relevance: 6 Novelty: 6
ArXiv ID: 2506.21416 Authors: Bowen Chen, Mengyi Zhao, Haomiao Sun, Li Chen, Xu Wang, Kang Du, Xinglong Wu
Abstract: Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.
Comment: Matches criterion 5 as it focuses on combining image generation tasks with semantic attributes, which aligns with integration of image and large language models. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21277 Authors: Qize Yang, Shimin Yao, Weixuan Chen, Shenghao Fu, Detao Bai, Jiaxing Zhao, Boyuan Sun, Bowen Yin, Xihan Wei, Jingren Zhou
Abstract: With the rapid evolution of multimodal large language models, the capacity to deeply understand and interpret human intentions has emerged as a critical capability, which demands detailed and thoughtful reasoning. In recent studies, Reinforcement Learning (RL) has demonstrated potential in enhancing the reasoning capabilities of Large Language Models (LLMs). Nonetheless, the challenges associated with adapting RL to multimodal data and formats remain largely unaddressed. In this paper, we identify two issues in existing multimodal reasoning models: insufficient global context understanding and shortcut problems. Insufficient context understanding can happen when a model misinterprets multimodal context, resulting in incorrect answers. The shortcut problem occurs when the model overlooks crucial clues in multimodal inputs, directly addressing the query without considering the multimodal information. To tackle these issues, we emphasize the necessity for the model to reason with a clear understanding of the global context within multimodal inputs. This global context understanding can effectively prevent the model from overlooking key multimodal cues and ensure a thorough reasoning process. To ensure the accurate interpretation of multimodal context information, we implement a context reward judged by a large language model, alongside format and accuracy rewards. Additionally, to improve complex reasoning capability, we employ the LLM to assess the logical reward, determining whether the reasoning process successfully integrates multimodal information with logical methods. We also introduce a reasoning omni-modal benchmark, IntentBench, aimed at evaluating models in understanding complex human intentions and emotions. Our proposed method demonstrates advanced performance across multiple omni-modal benchmarks compared to other open-source omni-modal models.
Comment: Matches criterion 2 as it explores multimodal reasoning in large language models, which aligns with vision and multimodal large language models. Relevance: 5 Novelty: 6
ArXiv ID: 2506.20879 Authors: Shubhankar Borse, Seokeon Choi, Sunghyun Park, Jeongho Kim, Shreya Kadambi, Risheek Garrepalli, Sungrack Yun, Munawar Hayat, Fatih Porikli
Abstract: Generation of images containing multiple humans, performing complex actions, while preserving their facial identities, is a significant challenge. A major factor contributing to this is the lack of a a dedicated benchmark. To address this, we introduce MultiHuman-Testbench, a novel benchmark for rigorously evaluating generative models for multi-human generation. The benchmark comprises 1800 samples, including carefully curated text prompts, describing a range of simple to complex human actions. These prompts are matched with a total of 5,550 unique human face images, sampled uniformly to ensure diversity across age, ethnic background, and gender. Alongside captions, we provide human-selected pose conditioning images which accurately match the prompt. We propose a multi-faceted evaluation suite employing four key metrics to quantify face count, ID similarity, prompt alignment, and action detection. We conduct a thorough evaluation of a diverse set of models, including zero-shot approaches and training-based methods, with and without regional priors. We also propose novel techniques to incorporate image and region isolation using human segmentation and Hungarian matching, significantly improving ID similarity. Our proposed benchmark and key findings provide valuable insights and a standardized tool for advancing research in multi-human image generation.
Comment: Matches criterion 3 as it introduces a new benchmark for multi-human image generation, which is relevant to embodied/robotic AI. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21184 Authors: Minghao Qin, Yan Shu, Peitian Zhang, Kun Lun, Huaying Yuan, Juenjie Zhou, Shitao Xiao, Bo Zhao, Zheng Liu
Abstract: Long-video understanding (LVU) remains a severe challenge for existing multimodal large language models (MLLMs), primarily due to the prohibitive computational cost. Recent approaches have explored KV compression to mitigate this issue, but they often suffer from significant information loss at high compression ratios. In this paper, we introduce Video-X^2L, which flexibly preserves critical video information for each LVU task. Video-X^2L involves two key operations. The first one is called bi-level KV compression. During the MLLM's pre-filling stage, Video-X^2L generates two types of compressed KVs: low-compression KVs (L-KVs) to capture fine-grained video details and high-compression KVs (H-KVs) to offer compact video representations. The second one is called selective KV re-loading. During the MLLM's decoding stage, Video-X^2L selectively re-loads L-KVs for the most critical video chunks while using H-KVs for other less important ones. This allows the MLLM to fully utilize task-specific information while maintaining the overall compactness. Video-X^2L is simple yet effective: it is free from additional training and directly compatible with existing KV-compressible MLLMs. We evaluate Video-X^2L with a variety of popular LVU benchmarks, including VideoMME, MLVU, LongVideoBench, and VNBench. Our experiment result shows that Video-X^2L outperforms existing KV-compression methods by a huge advantage while substantially saving the computation cost.
Comment: Matches criterion 6 as it proposes a cost-effective method for long video understanding in multimodal large language models. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21356 Authors: Hongbo Liu, Jingwen He, Yi Jin, Dian Zheng, Yuhao Dong, Fan Zhang, Ziqi Huang, Yinan He, Yangguang Li, Weichao Chen, Yu Qiao, Wanli Ouyang, Shengjie Zhao, Ziwei Liu
Abstract: Cinematography, the fundamental visual language of film, is essential for conveying narrative, emotion, and aesthetic quality. While recent Vision-Language Models (VLMs) demonstrate strong general visual understanding, their proficiency in comprehending the nuanced cinematic grammar embedded within individual shots remains largely unexplored and lacks robust evaluation. This critical gap limits both fine-grained visual comprehension and the precision of AI-assisted video generation. To address this, we introduce \textbf{ShotBench}, a comprehensive benchmark specifically designed for cinematic language understanding. It features over 3.5k expert-annotated QA pairs from images and video clips, meticulously curated from over 200 acclaimed (predominantly Oscar-nominated) films and spanning eight key cinematography dimensions. Our evaluation of 24 leading VLMs on ShotBench reveals their substantial limitations: even the top-performing model achieves less than 60% average accuracy, particularly struggling with fine-grained visual cues and complex spatial reasoning. To catalyze advancement in this domain, we construct \textbf{ShotQA}, a large-scale multimodal dataset comprising approximately 70k cinematic QA pairs. Leveraging ShotQA, we develop \textbf{ShotVL} through supervised fine-tuning and Group Relative Policy Optimization. ShotVL significantly outperforms all existing open-source and proprietary models on ShotBench, establishing new \textbf{state-of-the-art} performance. We open-source our models, data, and code to foster rapid progress in this crucial area of AI-driven cinematic understanding and generation.
Comment: Matches criterion 6 as it introduces a benchmark for cinematic understanding in vision-language models, focusing on video-based tasks. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21316 Authors: Badri Vishal Kasuba, Parag Chaudhuri, Ganesh Ramakrishnan
Abstract: Visual grounding in text-rich document images is a critical yet underexplored challenge for document intelligence and visual question answering (VQA) systems. We present \drishtikon, a multi-granular visual grounding framework designed to enhance interpretability and trust in VQA for complex, multilingual documents. Our approach integrates robust multi-lingual OCR, large language models, and a novel region matching algorithm to accurately localize answer spans at block, line, word, and point levels. We curate a new benchmark from the CircularsVQA test set, providing fine-grained, human-verified annotations across multiple granularities. Extensive experiments demonstrate that our method achieves state-of-the-art grounding accuracy, with line-level granularity offering the best trade-off between precision and recall. Ablation studies further highlight the benefits of multi-block and multi-line reasoning. Comparative evaluations with leading vision-language models reveal the limitations of current VLMs in precise localization, underscoring the effectiveness of our structured, alignment-based approach. Our findings pave the way for more robust and interpretable document understanding systems in real-world, text-centric scenarios. Code and dataset has been made available at https://github.com/kasuba-badri-vishal/DhrishtiKon.
Comment: Matches criterion 5 as it integrates image understanding tasks with large language models for document visual grounding. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21188 Authors: Zijun Lin, Shuting He, Cheston Tan, Bihan Wen
Abstract: Sequential grounding in 3D point clouds (SG3D) refers to locating sequences of objects by following text instructions for a daily activity with detailed steps. Current 3D visual grounding (3DVG) methods treat text instructions with multiple steps as a whole, without extracting useful temporal information from each step. However, the instructions in SG3D often contain pronouns such as "it", "here" and "the same" to make language expressions concise. This requires grounding methods to understand the context and retrieve relevant information from previous steps to correctly locate object sequences. Due to the lack of an effective module for collecting related historical information, state-of-the-art 3DVG methods face significant challenges in adapting to the SG3D task. To fill this gap, we propose GroundFlow -- a plug-in module for temporal reasoning on 3D point cloud sequential grounding. Firstly, we demonstrate that integrating GroundFlow improves the task accuracy of 3DVG baseline methods by a large margin (+7.5% and +10.2%) in the SG3D benchmark, even outperforming a 3D large language model pre-trained on various datasets. Furthermore, we selectively extract both short-term and long-term step information based on its relevance to the current instruction, enabling GroundFlow to take a comprehensive view of historical information and maintain its temporal understanding advantage as step counts increase. Overall, our work introduces temporal reasoning capabilities to existing 3DVG models and achieves state-of-the-art performance in the SG3D benchmark across five datasets.
Comment: Matches criterion 1 as it proposes a temporal reasoning module for 3D point cloud sequential grounding, which involves spatial intelligence. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21490 Authors: Tin Dizdarevi'c, Ravi Hammond, Tobias Gessler, Anisoara Calinescu, Jonathan Cook, Matteo Gallici, Andrei Lupu, Jakob Nicolaus Foerster
Abstract: Achieving seamless coordination between AI agents and humans is crucial for real-world applications, yet it remains a significant open challenge. Hanabi is a cooperative card game featuring imperfect information, constrained communication, theory of mind requirements, and coordinated action -- making it an ideal testbed for human-AI coordination. However, its use for human-AI interaction has been limited by the challenges of human evaluation. In this work, we introduce the Ad-Hoc Human-AI Coordination Challenge (AH2AC2) to overcome the constraints of costly and difficult-to-reproduce human evaluations. We develop \textit{human proxy agents} on a large-scale human dataset that serve as robust, cheap, and reproducible human-like evaluation partners in AH2AC2. To encourage the development of data-efficient methods, we open-source a dataset of 3,079 games, deliberately limiting the amount of available human gameplay data. We present baseline results for both two- and three- player Hanabi scenarios. To ensure fair evaluation, we host the proxy agents through a controlled evaluation system rather than releasing them publicly. The code is available at \href{https://github.com/FLAIROx/ah2ac2}{https://github.com/FLAIROx/ah2ac2}.
Comment: Matches criterion 3 as it introduces a new benchmark for human-AI coordination in the Hanabi game, relevant to embodied AI. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21080 Authors: Sanjoy Chowdhury, Subrata Biswas, Sayan Nag, Tushar Nagarajan, Calvin Murdock, Ishwarya Ananthabhotla, Yijun Qian, Vamsi Krishna Ithapu, Dinesh Manocha, Ruohan Gao
Abstract: Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment, especially in resource-constrained environments. In this paper, we introduce EgoAdapt, a framework that adaptively performs cross-modal distillation and policy learning to enable efficient inference across different egocentric perception tasks, including egocentric action recognition, active speaker localization, and behavior anticipation. Our proposed policy module is adaptable to task-specific action spaces, making it broadly applicable. Experimental results on three challenging egocentric datasets EPIC-Kitchens, EasyCom, and Aria Everyday Activities demonstrate that our method significantly enhances efficiency, reducing GMACs by up to 89.09%, parameters up to 82.02%, and energy up to 9.6x, while still on-par and in many cases outperforming, the performance of corresponding state-of-the-art models.
Comment: Matches criterion 3 as it introduces a novel framework for efficient egocentric perception tasks, which is relevant to embodied AI. Relevance: 5 Novelty: 6
ArXiv ID: 2506.20991 Authors: Chade Li, Pengju Zhang, Yihong Wu
Abstract: The rapid advancement of 3D vision-language models (VLMs) has spurred significant interest in interactive point cloud processing tasks, particularly for real-world applications. However, existing methods often underperform in point-level tasks, such as segmentation, due to missing direct 3D-text alignment, limiting their ability to link local 3D features with textual context. To solve this problem, we propose TSDASeg, a Two-Stage model coupled with a Direct cross-modal Alignment module and memory module for interactive point cloud Segmentation. We introduce the direct cross-modal alignment module to establish explicit alignment between 3D point clouds and textual/2D image data. Within the memory module, we employ multiple dedicated memory banks to separately store text features, visual features, and their cross-modal correspondence mappings. These memory banks are dynamically leveraged through self-attention and cross-attention mechanisms to update scene-specific features based on prior stored data, effectively addressing inconsistencies in interactive segmentation results across diverse scenarios. Experiments conducted on multiple 3D instruction, reference, and semantic segmentation datasets demonstrate that the proposed method achieves state-of-the-art performance.
Comment: Matches criterion 3 as it proposes a novel method for interactive point cloud segmentation, which is relevant to embodied/robotic AI. Relevance: 5 Novelty: 6
ArXiv ID: 2506.20960 Authors: Yiman Zhang, Ziheng Luo, Qiangyu Yan, Wei He, Borui Jiang, Xinghao Chen, Kai Han
Abstract: In this paper, we introduce OmniEval, a benchmark for evaluating omni-modality models like MiniCPM-O 2.6, which encompasses visual, auditory, and textual inputs. Compared with existing benchmarks, our OmniEval has several distinctive features: (i) Full-modal collaboration: We design evaluation tasks that highlight the strong coupling between audio and video, requiring models to effectively leverage the collaborative perception of all modalities; (ii) Diversity of videos: OmniEval includes 810 audio-visual synchronized videos, 285 Chinese videos and 525 English videos; (iii) Diversity and granularity of tasks: OmniEval contains 2617 question-answer pairs, comprising 1412 open-ended questions and 1205 multiple-choice questions. These questions are divided into 3 major task types and 12 sub-task types to achieve comprehensive evaluation. Among them, we introduce a more granular video localization task named Grounding. Then we conduct experiments on OmniEval with several omni-modality models. We hope that our OmniEval can provide a platform for evaluating the ability to construct and understand coherence from the context of all modalities. Codes and data could be found at https://omnieval.github.io/.
Comment: Matches criterion 2 as it introduces a benchmark (OmniEval) for evaluating multimodal models, which is relevant to vision–language integration. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21393 Authors: Junwen Zhang, Pu Chen, Yin Zhang
Abstract: Multimodal understanding of tables in real-world contexts is challenging due to the complexity of structure, symbolic density, and visual degradation (blur, skew, watermarking, incomplete structures or fonts, multi-span or hierarchically nested layouts). Existing multimodal large language models (MLLMs) struggle with such WildStruct conditions, resulting in limited performance and poor generalization. To address these challenges, we propose TableMoE, a neuro-symbolic Mixture-of-Connector-Experts (MoCE) architecture specifically designed for robust, structured reasoning over multimodal table data. TableMoE features an innovative Neuro-Symbolic Routing mechanism, which predicts latent semantic token roles (e.g., header, data cell, axis, formula) and dynamically routes table elements to specialized experts (Table-to-HTML, Table-to-JSON, Table-to-Code) using a confidence-aware gating strategy informed by symbolic reasoning graphs. To facilitate effective alignment-driven pretraining, we introduce the large-scale TableMoE-Align dataset, consisting of 1.2M table-HTML-JSON-code quadruples across finance, science, biomedicine and industry, utilized exclusively for model pretraining. For evaluation, we curate and release four challenging WildStruct benchmarks: WMMFinQA, WMMTatQA, WMMTabDialog, and WMMFinanceMath, designed specifically to stress-test models under real-world multimodal degradation and structural complexity. Experimental results demonstrate that TableMoE significantly surpasses existing state-of-the-art models. Extensive ablation studies validate each core component, emphasizing the critical role of Neuro-Symbolic Routing and structured expert alignment. Through qualitative analyses, we further showcase TableMoE's interpretability and enhanced robustness, underscoring the effectiveness of integrating neuro-symbolic reasoning for multimodal table understanding.
Comment: Matches criterion 2 as it explores multimodal table understanding with a novel neuro-symbolic architecture, which is relevant to vision–language integration. Relevance: 5 Novelty: 6
ArXiv ID: 2506.20756 Authors: Haodong Li, Chen Wang, Jiahui Lei, Kostas Daniilidis, Lingjie Liu
Abstract: Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pre-trained video diffusion models with massive data. However, we argue that video depth estimation is not a naive extension of image depth estimation. The temporal consistency requirements for dynamic and static regions in videos are fundamentally different. Consistent video depth in static regions, typically backgrounds, can be more effectively achieved via stereo matching across all frames, which provides much stronger global 3D cues. While the consistency for dynamic regions still should be learned from large-scale video depth data to ensure smooth transitions, due to the violation of triangulation constraints. Based on these insights, we introduce StereoDiff, a two-stage video depth estimator that synergizes stereo matching for mainly the static areas with video depth diffusion for maintaining consistent depth transitions in dynamic areas. We mathematically demonstrate how stereo matching and video depth diffusion offer complementary strengths through frequency domain analysis, highlighting the effectiveness of their synergy in capturing the advantages of both. Experimental results on zero-shot, real-world, dynamic video depth benchmarks, both indoor and outdoor, demonstrate StereoDiff's SoTA performance, showcasing its superior consistency and accuracy in video depth estimation.
Comment: Matches criterion 6 as it focuses on video depth estimation, which is a video understanding task. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21514 Authors: Mohammed Rakib, Arunkumar Bagavathi
Abstract: Multimodal learning aims to leverage information from diverse data modalities to achieve more comprehensive performance. However, conventional multimodal models often suffer from modality imbalance, where one or a few modalities dominate model optimization, leading to suboptimal feature representation and underutilization of weak modalities. To address this challenge, we introduce Gradient-Guided Distillation (G$^{2}$D), a knowledge distillation framework that optimizes the multimodal model with a custom-built loss function that fuses both unimodal and multimodal objectives. G$^{2}$D further incorporates a dynamic sequential modality prioritization (SMP) technique in the learning process to ensure each modality leads the learning process, avoiding the pitfall of stronger modalities overshadowing weaker ones. We validate G$^{2}$D on multiple real-world datasets and show that G$^{2}$D amplifies the significance of weak modalities while training and outperforms state-of-the-art methods in classification and regression tasks. Our code is available at https://github.com/rAIson-Lab/G2D.
Comment: Matches criterion 2 as it explores multimodal learning with a novel distillation framework, which is relevant to vision–language integration. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21549 Authors: Alex Costanzino, Pierluigi Zama Ramirez, Luigi Lella, Matteo Ragaglia, Alessandro Oliva, Giuseppe Lisanti, Luigi Di Stefano
Abstract: We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS), where the task is to produce a voxel-based Anomaly Volume. Moreover, SiM3D focuses on a scenario of high interest in manufacturing: single-instance anomaly detection, where only one object, either real or synthetic, is available for training. In this respect, SiM3D stands out as the first ADS benchmark that addresses the challenge of generalising from synthetic training data to real test data. SiM3D includes a novel multimodal multiview dataset acquired using top-tier industrial sensors and robots. The dataset features multiview high-resolution images (12 Mpx) and point clouds (7M points) for 333 instances of eight types of objects, alongside a CAD model for each type. We also provide manually annotated 3D segmentation GTs for anomalous test samples. To establish reference baselines for the proposed multiview 3D ADS task, we adapt prominent singleview methods and assess their performance using novel metrics that operate on Anomaly Volumes.
Comment: Matches criterion 3 as it introduces a new benchmark (SiM3D) for 3D anomaly detection, which is relevant to embodied/robotic AI. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21506 Authors: Boyu Gou, Zanming Huang, Yuting Ning, Yu Gu, Michael Lin, Weijian Qi, Andrei Kopanev, Botao Yu, Bernal Jim'enez Guti'errez, Yiheng Shu, Chan Hee Song, Jiaman Wu, Shijie Chen, Hanane Nour Moussa, Tianshu Zhang, Jian Xie, Yifei Li, Tianci Xue, Zeyi Liao, Kai Zhang, Boyuan Zheng, Zhaowei Cai, Viktor Rozgic, Morteza Ziyadi, Huan Sun, Yu Su
Abstract: Agentic search such as Deep Research systems, where large language models autonomously browse the web, synthesize information, and return comprehensive citation-backed answers, represents a major shift in how users interact with web-scale information. While promising greater efficiency and cognitive offloading, the growing complexity and open-endedness of agentic search have outpaced existing evaluation benchmarks and methodologies, which largely assume short search horizons and static answers. In this paper, we introduce Mind2Web 2, a benchmark of 130 realistic, high-quality, and long-horizon tasks that require real-time web browsing and extensive information synthesis, constructed with over 1,000 hours of human labor. To address the challenge of evaluating time-varying and complex answers, we propose a novel Agent-as-a-Judge framework. Our method constructs task-specific judge agents based on a tree-structured rubric design to automatically assess both answer correctness and source attribution. We conduct a comprehensive evaluation of nine frontier agentic search systems and human performance, along with a detailed error analysis to draw insights for future development. The best-performing system, OpenAI Deep Research, can already achieve 50-70% of human performance while spending half the time, showing a great potential. Altogether, Mind2Web 2 provides a rigorous foundation for developing and benchmarking the next generation of agentic search systems.
Comment: Matches criterion 3 as it introduces a new benchmark (Mind2Web 2) for agentic search systems, which is relevant to embodied/robotic AI. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21233 Authors: Xiwei Xuan, Ziquan Deng, Kwan-Liu Ma
Abstract: Training-free open-vocabulary semantic segmentation (OVS) aims to segment images given a set of arbitrary textual categories without costly model fine-tuning. Existing solutions often explore attention mechanisms of pre-trained models, such as CLIP, or generate synthetic data and design complex retrieval processes to perform OVS. However, their performance is limited by the capability of reliant models or the suboptimal quality of reference sets. In this work, we investigate the largely overlooked data quality problem for this challenging dense scene understanding task, and identify that a high-quality reference set can significantly benefit training-free OVS. With this observation, we introduce a data-quality-oriented framework, comprising a data pipeline to construct a reference set with well-paired segment-text embeddings and a simple similarity-based retrieval to unveil the essential effect of data. Remarkably, extensive evaluations on ten benchmark datasets demonstrate that our method outperforms all existing training-free OVS approaches, highlighting the importance of data-centric design for advancing OVS without training. Our code is available at https://github.com/xiweix/ReME .
Comment: Matches criteria 7 (Vision-Focused Survey Papers) as it emphasizes a data-centric framework for open-vocabulary segmentation, which is a dense scene understanding task. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21348 Authors: Lojze Zust, Yohann Cabon, Juliette Marrie, Leonid Antsfeld, Boris Chidlovskii, Jerome Revaud, Gabriela Csurka
Abstract: Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing approaches typically leverage off-the-shelf models to extract per-frame 2D panoptic segmentations, before optimizing an implicit geometric representation (often based on NeRF) to integrate and fuse the 2D predictions. We argue that relying on 2D panoptic segmentation for a problem inherently 3D and multi-view is likely suboptimal as it fails to leverage the full potential of spatial relationships across views. In addition to requiring camera parameters, these approaches also necessitate computationally expensive test-time optimization for each scene. Instead, in this work, we propose a unified and integrated approach PanSt3R, which eliminates the need for test-time optimization by jointly predicting 3D geometry and multi-view panoptic segmentation in a single forward pass. Our approach builds upon recent advances in 3D reconstruction, specifically upon MUSt3R, a scalable multi-view version of DUSt3R, and enhances it with semantic awareness and multi-view panoptic segmentation capabilities. We additionally revisit the standard post-processing mask merging procedure and introduce a more principled approach for multi-view segmentation. We also introduce a simple method for generating novel-view predictions based on the predictions of PanSt3R and vanilla 3DGS. Overall, the proposed PanSt3R is conceptually simple, yet fast and scalable, and achieves state-of-the-art performance on several benchmarks, while being orders of magnitude faster than existing methods.
Comment: Matches criteria 4 (Vision Foundation Models and Their Applications) as it focuses on multi-view panoptic segmentation using foundational 3D reconstruction models. Relevance: 5 Novelty: 6
ArXiv ID: 2506.21444 Authors: Sweta Banerjee, Viktoria Weiss, Taryn A. Donovan, Rutger A. Fick, Thomas Conrad, Jonas Ammeling, Nils Porsche, Robert Klopfleisch, Christopher Kaltenecker, Katharina Breininger, Marc Aubreville, Christof A. Bertram
Abstract: Atypical mitoses mark a deviation in the cell division process that can be an independent prognostically relevant marker for tumor malignancy. However, their identification remains challenging due to low prevalence, at times subtle morphological differences from normal mitoses, low inter-rater agreement among pathologists, and class imbalance in datasets. Building on the Atypical Mitosis dataset for Breast Cancer (AMi-Br), this study presents a comprehensive benchmark comparing deep learning approaches for automated atypical mitotic figure (AMF) classification, including baseline models, foundation models with linear probing, and foundation models fine-tuned with low-rank adaptation (LoRA). For rigorous evaluation, we further introduce two new hold-out AMF datasets - AtNorM-Br, a dataset of mitoses from the The TCGA breast cancer cohort, and AtNorM-MD, a multi-domain dataset of mitoses from the MIDOG++ training set. We found average balanced accuracy values of up to 0.8135, 0.7696, and 0.7705 on the in-domain AMi-Br and the out-of-domain AtNorm-Br and AtNorM-MD datasets, respectively, with the results being particularly good for LoRA-based adaptation of the Virchow-line of foundation models. Our work shows that atypical mitosis classification, while being a challenging problem, can be effectively addressed through the use of recent advances in transfer learning and model fine-tuning techniques. We make available all code and data used in this paper in this github repository: https://github.com/DeepMicroscopy/AMi-Br_Benchmark.
Comment: Matches criterion 4 as it benchmarks vision foundation models for a specific application in medical imaging. Relevance: 5 Novelty: 5
ArXiv ID: 2506.21329 Authors: Karthik Duraisamy
Abstract: The rapid evolution of artificial intelligence has led to expectations of transformative scientific discovery, yet current systems remain fundamentally limited by their operational architectures, brittle reasoning mechanisms, and their separation from experimental reality. Building on earlier work, we contend that progress in AI-driven science now depends on closing three fundamental gaps -- the abstraction gap, the reasoning gap, and the reality gap -- rather than on model size/data/test time compute. Scientific reasoning demands internal representations that support simulation of actions and response, causal structures that distinguish correlation from mechanism, and continuous calibration. We define active inference AI systems for scientific discovery as those that (i) maintain long-lived research memories grounded in causal self-supervised foundation models, (ii) symbolic or neuro-symbolic planners equipped with Bayesian guardrails, (iii) grow persistent knowledge graphs where thinking generates novel conceptual nodes, reasoning establishes causal edges, and real-world interaction prunes false connections while strengthening verified pathways, and (iv) refine their internal representations through closed-loop interaction with both high-fidelity simulators and automated laboratories - an operational loop where mental simulation guides action and empirical surprise reshapes understanding. In essence, we outline an architecture where discovery arises from the interplay between internal models that enable counterfactual reasoning and external validation that grounds hypotheses in reality. It is also argued that the inherent ambiguity in feedback from simulations and experiments, and underlying uncertainties makes human judgment indispensable, not as a temporary scaffold but as a permanent architectural component.
Comment: Does not closely match any specific criteria but discusses a novel architecture for scientific discovery with embodied reasoning elements. Relevance: 3 Novelty: 7
ArXiv ID: 2506.21401 Authors: Zhirui Gao. Renjiao Yi, Yaqiao Dai, Xuening Zhu, Wei Chen, Chenyang Zhu, Kai Xu
Abstract: This paper presents an end-to-end framework for reconstructing 3D parametric curves directly from multi-view edge maps. Contrasting with existing two-stage methods that follow a sequential ``edge point cloud reconstruction and parametric curve fitting'' pipeline, our one-stage approach optimizes 3D parametric curves directly from 2D edge maps, eliminating error accumulation caused by the inherent optimization gap between disconnected stages. However, parametric curves inherently lack suitability for rendering-based multi-view optimization, necessitating a complementary representation that preserves their geometric properties while enabling differentiable rendering. We propose a novel bi-directional coupling mechanism between parametric curves and edge-oriented Gaussian components. This tight correspondence formulates a curve-aware Gaussian representation, \textbf{CurveGaussian}, that enables differentiable rendering of 3D curves, allowing direct optimization guided by multi-view evidence. Furthermore, we introduce a dynamically adaptive topology optimization framework during training to refine curve structures through linearization, merging, splitting, and pruning operations. Comprehensive evaluations on the ABC dataset and real-world benchmarks demonstrate our one-stage method's superiority over two-stage alternatives, particularly in producing cleaner and more robust reconstructions. Additionally, by directly optimizing parametric curves, our method significantly reduces the parameter count during training, achieving both higher efficiency and superior performance compared to existing approaches.
Comment: Does not directly match any specific criterion but is relevant to 3D parametric curve reconstruction and computer vision. Relevance: 3 Novelty: 6
ArXiv ID: 2506.21076 Authors: Hongyu Yan, Kunming Luo, Weiyu Li, Yixun Liang, Shengming Li, Jingwei Huang, Chunchao Guo, Ping Tan
Abstract: 3D characters play a crucial role in our daily entertainment. To improve the efficiency of 3D character modeling, recent image-based methods use two separate models to achieve pose standardization and 3D reconstruction of the A-pose character. However, these methods are prone to generating distorted and degraded images in the pose standardization stage due to self-occlusion and viewpoints, which further affects the geometric quality of the subsequent reconstruction process. To tackle these problems, we propose PoseMaster, an end-to-end controllable 3D character generation framework. Specifically, we unify pose transformation and 3D character generation into a flow-based 3D native generation framework. To achieve accurate arbitrary-pose control, we propose to leverage the 3D body bones existing in the skeleton of an animatable character as the pose condition. Furthermore, considering the specificity of multi-condition control, we randomly empty the pose condition and the image condition during training to improve the effectiveness and generalizability of pose control. Finally, we create a high-quality pose-control dataset derived from realistic character animation data to make the model learning the implicit relationships between skeleton and skinning weights. Extensive experiments show that PoseMaster outperforms current state-of-the-art techniques in both qualitative and quantitative evaluations for A-pose character generation while demonstrating its powerful ability to achieve precise control for arbitrary poses.
Comment: Does not directly match any specific criterion but is relevant to computer vision and generative modeling. Relevance: 3 Novelty: 6
ArXiv ID: 2506.21513 Authors: Wentao Hu, Shunkai Li, Ziqiao Peng, Haoxian Zhang, Fan Shi, Xiaoqiang Liu, Pengfei Wan, Di Zhang, Hui Tian
Abstract: Creating high-quality, generalizable speech-driven 3D talking heads remains a persistent challenge. Previous methods achieve satisfactory results for fixed viewpoints and small-scale audio variations, but they struggle with large head rotations and out-of-distribution (OOD) audio. Moreover, they are constrained by the need for time-consuming, identity-specific training. We believe the core issue lies in the lack of sufficient 3D priors, which limits the extrapolation capabilities of synthesized talking heads. To address this, we propose GGTalker, which synthesizes talking heads through a combination of generalizable priors and identity-specific adaptation. We introduce a two-stage Prior-Adaptation training strategy to learn Gaussian head priors and adapt to individual characteristics. We train Audio-Expression and Expression-Visual priors to capture the universal patterns of lip movements and the general distribution of head textures. During the Customized Adaptation, individual speaking styles and texture details are precisely modeled. Additionally, we introduce a color MLP to generate fine-grained, motion-aligned textures and a Body Inpainter to blend rendered results with the background, producing indistinguishable, photorealistic video frames. Comprehensive experiments show that GGTalker achieves state-of-the-art performance in rendering quality, 3D consistency, lip-sync accuracy, and training efficiency.
Comment: Does not match any specific criteria but is tangentially related to generative modeling for talking head synthesis, which might be of general interest. Relevance: 3 Novelty: 6
ArXiv ID: 2506.20867 Authors: Ryosuke Kawamura, Hideaki Hayashi, Shunsuke Otake, Noriko Takemura, Hajime Nagahara
Abstract: Dynamic facial expression recognition (DFER) is a task that estimates emotions from facial expression video sequences. For practical applications, accurately recognizing ambiguous facial expressions -- frequently encountered in in-the-wild data -- is essential. In this study, we propose MIDAS, a data augmentation method designed to enhance DFER performance for ambiguous facial expression data using soft labels representing probabilities of multiple emotion classes. MIDAS augments training data by convexly combining pairs of video frames and their corresponding emotion class labels. This approach extends mixup to soft-labeled video data, offering a simple yet highly effective method for handling ambiguity in DFER. To evaluate MIDAS, we conducted experiments on both the DFEW dataset and FERV39k-Plus, a newly constructed dataset that assigns soft labels to an existing DFER dataset. The results demonstrate that models trained with MIDAS-augmented data achieve superior performance compared to the state-of-the-art method trained on the original dataset.
Comment: Does not directly match any specific criterion but is relevant to dynamic facial expression recognition and data augmentation. Relevance: 3 Novelty: 5
ArXiv ID: 2506.20900 Authors: Sherlon Almeida da Silva, Davi Geiger, Luiz Velho, Moacir Antonelli Ponti
Abstract: This work investigates the geometric foundations of modern stereo vision systems, with a focus on how 3D structure and human-inspired perception contribute to accurate depth reconstruction. We revisit the Cyclopean Eye model and propose novel geometric constraints that account for occlusions and depth discontinuities. Our analysis includes the evaluation of stereo feature matching quality derived from deep learning models, as well as the role of attention mechanisms in recovering meaningful 3D surfaces. Through both theoretical insights and empirical studies on real datasets, we demonstrate that combining strong geometric priors with learned features provides internal abstractions for understanding stereo vision systems.
Comment: Does not directly match any specific criterion but is relevant to stereo vision and geometric modeling. Relevance: 3 Novelty: 5
ArXiv ID: 2506.20841 Authors: Ha Min Son, Shahbaz Rezaei, Xin Liu
Abstract: Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform. Consequently, existing SSDG methods combine semi-supervised learning methods with various regularization terms. However, these methods do not explicitly regularize to learn domains invariant representations across all domains, which is a key goal for domain generalization. To address this, we introduce FixCLR. Inspired by success in self-supervised learning, we change two crucial components to adapt contrastive learning for explicit domain invariance regularization: utilization of class information from pseudo-labels and using only a repelling term. FixCLR can also be added on top of most existing SSDG and semi-supervised methods for complementary performance improvements. Our research includes extensive experiments that have not been previously explored in SSDG studies. These experiments include benchmarking different improvements to semi-supervised methods, evaluating the performance of pretrained versus non-pretrained models, and testing on datasets with many domains. Overall, FixCLR proves to be an effective SSDG method, especially when combined with other semi-supervised methods.
Comment: Does not match any specific criterion but is relevant to domain generalization and semi-supervised learning. Relevance: 3 Novelty: 5
ArXiv ID: 2506.21215 Authors: Haoang Chi, He Li, Wenjing Yang, Feng Liu, Long Lan, Xiaoguang Ren, Tongliang Liu, Bo Han
Abstract: Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing responses that obey the laws of causality, it remains unclear whether they perform genuine causal reasoning akin to humans. However, current evidence indicates the contrary. Specifically, LLMs are only capable of performing shallow (level-1) causal reasoning, primarily attributed to the causal knowledge embedded in their parameters, but they lack the capacity for genuine human-like (level-2) causal reasoning. To support this hypothesis, methodologically, we delve into the autoregression mechanism of transformer-based LLMs, revealing that it is not inherently causal. Empirically, we introduce a new causal Q&A benchmark called CausalProbe-2024, whose corpora are fresh and nearly unseen for the studied LLMs. The LLMs exhibit a significant performance drop on CausalProbe-2024 compared to earlier benchmarks, indicating the fact that they primarily engage in level-1 causal reasoning. To bridge the gap towards level-2 causal reasoning, we draw inspiration from the fact that human reasoning is usually facilitated by general knowledge and intended goals. We propose G^2-Reasoner, a method that incorporates general knowledge and goal-oriented prompts into LLMs' causal reasoning processes. Experiments demonstrate that G^2-Reasoner significantly enhances LLMs' causal reasoning capability, particularly in fresh and counterfactual contexts. This work sheds light on a new path for LLMs to advance towards genuine causal reasoning, going beyond level-1 and making strides towards level-2.
Comment: Does not match any specific criterion but is relevant to large language models and reasoning capabilities. Relevance: 3 Novelty: 5
ArXiv ID: 2506.20949 Authors: Chenkai Sun, Denghui Zhang, ChengXiang Zhai, Heng Ji
Abstract: Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We propose a proof-of-concept framework that projects how model-generated advice could propagate through societal systems on a macroscopic scale over time, enabling more robust alignment. To assess the long-term safety awareness of language models, we also introduce a dataset of 100 indirect harm scenarios, testing models' ability to foresee adverse, non-obvious outcomes from seemingly harmless user prompts. Our approach achieves not only over 20% improvement on the new dataset but also an average win rate exceeding 70% against strong baselines on existing safety benchmarks (AdvBench, SafeRLHF, WildGuardMix), suggesting a promising direction for safer agents.
Comment: Does not match any specific criterion but is relevant to language model alignment and safety, which is tangentially related to embodied AI. Relevance: 3 Novelty: 5
ArXiv ID: 2506.21132 Authors: Hai Jiang, Binhao Guan, Zhen Liu, Xiaohong Liu, Jian Yu, Zheng Liu, Songchen Han, Shuaicheng Liu
Abstract: Learning-based methods have made promising advances in low-light RAW image enhancement, while their capability to extremely dark scenes where the environmental illuminance drops as low as 0.0001 lux remains to be explored due to the lack of corresponding datasets. To this end, we propose a paired-to-paired data synthesis pipeline capable of generating well-calibrated extremely low-light RAW images at three precise illuminance ranges of 0.01-0.1 lux, 0.001-0.01 lux, and 0.0001-0.001 lux, together with high-quality sRGB references to comprise a large-scale paired dataset named See-in-the-Extremely-Dark (SIED) to benchmark low-light RAW image enhancement approaches. Furthermore, we propose a diffusion-based framework that leverages the generative ability and intrinsic denoising property of diffusion models to restore visually pleasing results from extremely low-SNR RAW inputs, in which an Adaptive Illumination Correction Module (AICM) and a color consistency loss are introduced to ensure accurate exposure correction and color restoration. Extensive experiments on the proposed SIED and publicly available benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/JianghaiSCU/SIED.
Comment: Does not match any specific criterion but is relevant to computer vision and low-light image enhancement. Relevance: 3 Novelty: 5
ArXiv ID: 2506.20977 Authors: Tao Liu, Dafeng Zhang, Gengchen Li, Shizhuo Liu, Yongqi Song, Senmao Li, Shiqi Yang, Boqian Li, Kai Wang, Yaxing Wang
Abstract: Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing age accuracy and identity preservation--what we refer to as the Age-ID trade-off. Most prior methods either prioritize age transformation at the expense of identity consistency or vice versa. In this work, we address this issue by proposing a two-pass face aging framework, named Cradle2Cane, based on few-step text-to-image (T2I) diffusion models. The first pass focuses on solving age accuracy by introducing an adaptive noise injection (AdaNI) mechanism. This mechanism is guided by including prompt descriptions of age and gender for the given person as the textual condition. Also, by adjusting the noise level, we can control the strength of aging while allowing more flexibility in transforming the face. However, identity preservation is weakly ensured here to facilitate stronger age transformations. In the second pass, we enhance identity preservation while maintaining age-specific features by conditioning the model on two identity-aware embeddings (IDEmb): SVR-ArcFace and Rotate-CLIP. This pass allows for denoising the transformed image from the first pass, ensuring stronger identity preservation without compromising the aging accuracy. Both passes are jointly trained in an end-to-end way. Extensive experiments on the CelebA-HQ test dataset, evaluated through Face++ and Qwen-VL protocols, show that our Cradle2Cane outperforms existing face aging methods in age accuracy and identity consistency.
Comment: Does not closely match any specific criterion but is related to generative modeling in computer vision. Relevance: 3 Novelty: 5
ArXiv ID: 2506.21012 Authors: Huan Wang, Haoran Li, Huaming Chen, Jun Yan, Jiahua Shi, Jun Shen
Abstract: Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving. However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at multiple clients. A number of existing FL methods attempt to tackle data heterogeneity locally (e.g., regularizing local models) or globally (e.g., fine-tuning global model), often neglecting inherent semantic information contained in each client. To explore the possibility of using intra-client semantically meaningful knowledge in handling data heterogeneity, in this paper, we propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients. The core idea of FedSC is to construct relational prototypes and consistent prototypes at semantic-level, aiming to provide fruitful class underlying knowledge and stable convergence signals in a prototype-wise collaborative way. On the one hand, FedSC introduces an inter-contrastive learning strategy to bring instance-level embeddings closer to relational prototypes with the same semantics and away from distinct classes. On the other hand, FedSC devises consistent prototypes via a discrepancy aggregation manner, as a regularization penalty to constrain the optimization region of the local model. Moreover, a theoretical analysis for FedSC is provided to ensure a convergence guarantee. Experimental results on various challenging scenarios demonstrate the effectiveness of FedSC and the efficiency of crucial components.
Comment: Does not closely match any specific criterion but is related to federated learning and machine learning. Relevance: 3 Novelty: 5
ArXiv ID: 2506.21452 Authors: Kaiyu Song, Hanjiang Lai
Abstract: Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of the conditional term. However, the high guidance scale often results in oversaturation and unrealistic artifacts. In this paper, we introduce a new perspective based on low-frequency signals, identifying the accumulation of redundant information in these signals as the key factor behind oversaturation and unrealistic artifacts. Building on this insight, we propose low-frequency improved classifier-free guidance (LF-CFG) to mitigate these issues. Specifically, we introduce an adaptive threshold-based measurement to pinpoint the locations of redundant information. We determine a reasonable threshold by analyzing the change rate of low-frequency information between prior and current steps. We then apply a down-weight strategy to reduce the impact of redundant information in the low-frequency signals. Experimental results demonstrate that LF-CFG effectively alleviates oversaturation and unrealistic artifacts across various diffusion models, including Stable Diffusion-XL, Stable Diffusion 2.1, 3.0, 3.5, and SiT-XL.
Comment: Does not closely match any specific criterion but is related to diffusion models and generative modeling. Relevance: 3 Novelty: 5
ArXiv ID: 2506.21150 Authors: Junwen Wang, Oscar Maccormac, William Rochford, Aaron Kujawa, Jonathan Shapey, Tom Vercauteren
Abstract: Hyperspectral imaging (HSI) shows great promise for surgical applications, offering detailed insights into biological tissue differences beyond what the naked eye can perceive. Refined labelling efforts are underway to train vision systems to distinguish large numbers of subtly varying classes. However, commonly used learning methods for biomedical segmentation tasks penalise all errors equivalently and thus fail to exploit any inter-class semantics in the label space. In this work, we introduce two tree-based semantic loss functions which take advantage of a hierarchical organisation of the labels. We further incorporate our losses in a recently proposed approach for training with sparse, background-free annotations. Extensive experiments demonstrate that our proposed method reaches state-of-the-art performance on a sparsely annotated HSI dataset comprising $107$ classes organised in a clinically-defined semantic tree structure. Furthermore, our method enables effective detection of out-of-distribution (OOD) pixels without compromising segmentation performance on in-distribution (ID) pixels.
Comment: Does not closely match any specific criterion but is related to computer vision and machine learning. Relevance: 3 Novelty: 5
ArXiv ID: 2506.20737 Authors: Gurusha Juneja, Alon Albalak, Wenyue Hua, William Yang Wang
Abstract: The proliferation of LLM-based agents has led to increasing deployment of inter-agent collaboration for tasks like scheduling, negotiation, resource allocation etc. In such systems, privacy is critical, as agents often access proprietary tools and domain-specific databases requiring strict confidentiality. This paper examines whether LLM-based agents demonstrate an understanding of contextual privacy. And, if instructed, do these systems preserve inference time user privacy in non-adversarial multi-turn conversation. Existing benchmarks to evaluate contextual privacy in LLM-agents primarily assess single-turn, low-complexity tasks where private information can be easily excluded. We first present a benchmark - MAGPIE comprising 158 real-life high-stakes scenarios across 15 domains. These scenarios are designed such that complete exclusion of private data impedes task completion yet unrestricted information sharing could lead to substantial losses. We then evaluate the current state-of-the-art LLMs on (a) their understanding of contextually private data and (b) their ability to collaborate without violating user privacy. Empirical experiments demonstrate that current models, including GPT-4o and Claude-2.7-Sonnet, lack robust understanding of contextual privacy, misclassifying private data as shareable 25.2% and 43.6% of the time. In multi-turn conversations, these models disclose private information in 59.9% and 50.5% of cases even under explicit privacy instructions. Furthermore, multi-agent systems fail to complete tasks in 71% of scenarios. These results underscore that current models are not aligned towards both contextual privacy preservation and collaborative task-solving.
Comment: Does not match any specific criteria but is tangentially related to multi-agent systems and privacy, which might be of general interest. Relevance: 3 Novelty: 5
ArXiv ID: 2506.21091 Authors: Mahmoud Tahmasebi, Saif Huq, Kevin Meehan, Marion McAfee
Abstract: Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models that deliver high accuracy while operating in real-time continues to be a major challenge in computer vision. In the domain of cost-volume-based stereo matching, accurate disparity estimation depends heavily on large-scale cost volumes. However, such large volumes store substantial redundant information and also require computationally intensive aggregation units for processing and regression, making real-time performance unattainable. Conversely, small-scale cost volumes followed by lightweight aggregation units provide a promising route for real-time performance, but lack sufficient information to ensure highly accurate disparity estimation. To address this challenge, we propose the Enhanced Shuffle Mixer (ESM) to mitigate information loss associated with small-scale cost volumes. ESM restores critical details by integrating primary features into the disparity upsampling unit. It quickly extracts features from the initial disparity estimation and fuses them with image features. These features are mixed by shuffling and layer splitting then refined through a compact feature-guided hourglass network to recover more detailed scene geometry. The ESM focuses on local contextual connectivity with a large receptive field and low computational cost, leading to the reconstruction of a highly accurate disparity map at real-time. The compact version of ESMStereo achieves an inference speed of 116 FPS on high-end GPUs and 91 FPS on the AGX Orin.
Comment: Does not match any specific criterion but is relevant to computer vision and machine learning in stereo matching. 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.