Visually Grounded Reasoning

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 183% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 286

All topics

ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination
Aug 5, 2026Lei Peng, Shuai Lv, Wei HuVLM Reasoning Visually Grounded Reasoning
University of Science and Technology of China School of Artificial Intelligence and Data Science Hefei, Anhui, China · University of Science and Technology of China State Key Laboratory of Precision and Intelligent Chemistry Hefei, Anhui, China
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
Aug 3, 2026Xuehang Guo, Pingyue Zhang, Ruiyi Zhang +6Data Visualization Chart QA
1William & Mary · 2Northwestern University · 3Adobe +1
DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3AI Agent Reliability VLM Interpretability
University of Electronic Science and Technology of China, Chengdu, China.
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
Jul 31, 2026Binnan Liu, Yechi Ma, Tian Xie +1Visual Reasoning Visually Grounded Reasoning
1Zhejiang University · 2Zhejiang Lab
Visual Credit Audit for Multimodal Spatial Reasoning
Jul 29, 2026Feixiang Liu, Qiang Qiu, Lanbo Sun +3VLM Evaluation Spatial Reasoning Benchmarks
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences
SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data
Jul 22, 2026Wael AbdAlmageedVisually Grounded Reasoning Neuro-Symbolic Reasoning
Holcombe Department of Electrical and Computer Engineering, Clemson University
SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning
Jul 15, 2026Cheng Tang, Junzhi Ning, Min Cen +9Reinforcement Learning with Verifiable Rewards Visually Grounded Reasoning
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Sichuan University +2
UniVR: Thinking in Visual Space for Unified Visual Reasoning
Jul 14, 2026Zhongwei Ren, Yunchao Wei, Yao Zhao +5Physical Reasoning Visual Spatial Reasoning
Beijing Jiaotong University · ByteDance
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
Jul 13, 2026Kaixin Ma, Di Feng, Alexander Metz +3Tool-Use Evaluation Tool-Using Vision-Language Agents
Apple
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
Jul 13, 2026Wencheng Ye, Yi Bin, Yujuan Ding +7VLM Interpretability Multimodal Reasoning
School of Computer Science and Technology, Tongji University · School of Fashion and Textiles, The Hong Kong Polytechnic University · School of Artificial Intelligence, Shanghai Jiao Tong University
OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
Jul 10, 2026Yang Chen, Yunwen Li, Yufan Shen +6VLM Evaluation Document Understanding
Shanghai Artificial Intelligence Laboratory · Zhejiang University · M-A-P +2
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
Jul 9, 2026Sophia Koehler, Antonia Wüst, Inga Ibs +5AI Agent Evaluation Active Learning
1AIML Lab, TU Darmstadt · 2Hessian Center for AI (hessian.AI) · Psychology of Information Processing, TU Darmstadt +4
APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts
Jul 9, 2026Emily Jin, Joy Hsu, Yiqing Xu +3Visual Spatial Reasoning Long-Horizon Robotic Manipulation
Stanford University
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
Jul 7, 2026Han-Jun Ko, Jr-Jen Chen, Haobo Yuan +4Physical Reasoning VLM Reasoning
National Taiwan University · The University of California, Merced
Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning
Jul 7, 2026Yake Wei, Yuan Wang, Fengyun Rao +2Vision-Language Grounding VLM Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China · Laboratory of Research on Large Models and Intelligent Governance · Tsinghua University +1
Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models
Jul 7, 2026Zhiwei Yang, Yuanchen Wu, Nan Zhang +3Multimodal Large Language Models Multimodal CoT Reasoning
Tencent Youtu Lab, Shanghai, China · Fudan University, Shanghai, China
Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies
Jul 6, 2026Adrian Szvoren, Dimitrios Kanoulas, Nilufer TuptukVisual Navigation Vision-Language Navigation
Department of Computer Science University College London · Department of Security and Crime Science University College London
EventCoT: Event-centric Video Chain-of-thought for Reasoning Temporal Localization
Jul 6, 2026Youngkil Song, Yoonjae Baek, Dongwon Kim +3Temporal Video Grounding Multimodal CoT Reasoning
1Pohang University of Science and Technology, Pohang, South Korea · 2Korea Advanced Institute of Science and Technology, Daejeon, South Korea · 3Handong Global University, Pohang, South Korea
IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning
Jul 3, 2026Yuening Cai, Junwei Zhou, Youran Qu +1VLM Evaluation Spatial Reasoning Benchmarks
Department of Computer Science Dartmouth College
MentalThink: Shaping Thoughts in Mental SVG World
Jul 3, 2026Kangheng Lin, Jisheng Yin, Dingming Li +11Visual Spatial Reasoning Latent Visual Reasoning
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · University of Chinese Academy of Sciences · StepFun
R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables
Jul 3, 2026Maxwell Horton, Wei Lu, Quan Tran +6Spatial Reasoning Benchmarks 3D Spatial Reasoning
Meta Reality Labs
ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space
Jul 3, 2026Peiming Li, Yifan Wang, Xiaotian Zhang +4Multimodal Large Language Models Latent Visual Reasoning
Basic Algorithm Center, PCG, Tencent · Zhejiang University · Peking University
Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning
Jul 2, 2026Liyan Tang, Fangcong Yin, Greg DurrettVLM Robustness Vision-Language Models
The University of Texas at Austin · New York University
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Jul 1, 2026Hongxing Li, Xiufeng Huang, Dingming Li +11Visual Reasoning VLM Reasoning
1Zhejiang University · 2Alibaba Group
GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
Jul 1, 2026Dianyu Wang, Peirong Zhang, Xuyang Li +2Vision-Language Grounding VLM Reasoning
Aerospace Information Research Institute, the Key Laboratory of Network Information System Technology (NIST), and the Key Laboratory of Target Cognition and Application Technology (TCAT), Chinese Academy of Sciences, Beijing 100190, China · School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100190, China
Latent Visual Cache for Video Reasoning
Jul 1, 2026Yongheng Zhang, Zhipeng Xu, Hao Wu +4Memory-Augmented VLMs Vision-Language Models
1Tencent Youtu Lab · 2Tsinghua University · University of Illinois at Chicago
MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos
Jul 1, 2026Leyuan Yu, Xiao Tang, Minghao Liu +6VLM Evaluation Spatial Reasoning Benchmarks
ZODA · Tongji University · Zhejiang University +1
PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking
Jun 30, 2026Dengxian Gong, Yuanzheng Wu, Haobo Yuan +11Vision-Language Grounding Tool-Using Vision-Language Agents
Wuhan University · UC Merced · UTS +3
Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence
Jun 30, 2026Rui Hao, Qiankun Li, Junyuan Mao +4Radiology Report Generation Medical VQA
Huazhong University of Science and Technology, Wuhan, China · Imperial Global Singapore, Imperial College London, London, United Kingdom · Nanyang Technological University, Singapore, Singapore +2
Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning
Jun 30, 2026Chih-Ting Liao, Fei Shen, Xin Cao +1Visual Spatial Reasoning VLM Interpretability
University of New South Wales · National University of Singapore

Aug 5, 2026, cs.CVJ/K move · Enter open · S save

ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination

Lei Peng, Shuai Lv, Wei Hu

University of Science and Technology of China School of Artificial Intelligence and Data Science Hefei, Anhui, China · University of Science and Technology of China State Key Laboratory of Precision and Intelligent Chemistry Hefei, Anhui, China

VLM Reasoning Visually Grounded Reasoning

Open paper AskPDF arXiv

Vision-Language Models (VLMs) often lose visual grounding during multi-step reasoning: as reasoning chains grow longer, later inference steps rely increasingly on language priors rather than image evidence. We identify a consistent benchmark-level signature associated with this degradation: across 2,510 re-examined samples from four benchmarks, attention entropy over image tokens typically decreases during Round 1 and rises again after image re-injection. However, we find that effective visual re-examination requires two complementary ingredients: image re-injection and targeted self-diagnosis. Without targeted diagnosis, re-examination can even hurt performance, whereas accurate self-diagnosis yields substantial gains -- a swing of several points on key benchmarks, indicating that diagnostic quality is a key factor in whether re-examination helps or hurts in our setting. We present ReGround, a two-stage framework that teaches VLMs to self-diagnose grounding failures and selectively re-examine visual evidence, without architectural modifications or external tools. Through capability bootstrapping, a stronger variant from the same model family provides diagnostic scaffolding only during data construction, while the policy model learns to diagnose autonomously at inference time and retains most of the assisted gains. Experiments on eight benchmarks across two VLM backbones demonstrate consistent gains, especially on visually intensive multi-step reasoning tasks, while incurring only modest inference overhead relative to tool-augmented baselines. Project page: https://sespoir.github.io/reground-page/ . Code: https://github.com/sespoir/ReGround .

Momentum

Related topics

Latest papers 286