VLM Reasoning

VLM: Vision-Language Model

Follow this topic Ask about this topic

Momentum

70 papers in the last four weeks, up 250% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 541

All topics

Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy
Jun 2, 2026Soohyun Lee, Jaeyoung Kim, Seokhyeon Park +5VLM Evaluation Data Visualization
Seoul National University · MADI Co., Ltd. · Hankuk University of Foreign Studies +1
Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language Models
Jun 1, 2026Lexin Wang, Shenghua Liu, Yiwei Wang +2VLM Evaluation VLM Reasoning
Institute of Computing Technology, Chinese Academy of Sciences · University of California, Merced
InsightVQA: High-Dimensional Emotion-Cognitive Visual Question Answering Benchmark
Jun 1, 2026Shiyu Wang, Ziyu Liu, Chaoyi Yu +6VLM Evaluation Visual Question Answering
East China Normal University, Shanghai, China
Disentanglement-Based Equivariant Learning for Compositional VQA
Jun 1, 2026Zhou Du, Zhaoquan Yuan, Xiao Wu +1Visual Question Answering Disentangled Representation Learning
School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611730, China, and also with Engineering Research Center of Sustainable Urban Intelligence Transportation, Ministry of Education, China · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China, and with the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 101408, China, and also with Peng Cheng Laboratory, ShenZhen 518055, China
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
Jun 1, 2026Tianze Yang, Yucheng Shi, Ruitong Sun +3Reinforcement Learning VLM Reasoning
University of Georgia
TLG: Temporal-Logic Grounding for Video Question Answering via Source-Annotation Reconstruction and Category-Targeted Reasoning
Jun 1, 2026Ali AlaviTemporal Video Grounding Logical Reasoning
The Ohio State University
Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning
Jun 1, 2026Sanchit Sinha, Guangzhi Xiong, Bohan Liu +2Fine-Tuning Multimodal Large Language Models
University of Virginia
Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
May 31, 2026Garvin Guo, Yu Chen, Xiang Wang +4VLM Evaluation VLM Interpretability
Amap, Alibaba Group · Shanghai Innovation Institute
Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning
May 31, 2026Jixuan He, Xueting Li, Chieh Hubert Lin +13D Spatial Reasoning VLM Reasoning
Cornell Tech, Cornell University · NVIDIA · illoca AI +1
Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion
May 30, 2026Shivam Singh, Saptarshi Majumder, Pratik Prabhanjan Brahma +2Vision-Language Grounding Video Reasoning
IIIT Hyderabad · Work done during Shivam Singh’s internship at Advanced Micro Devices, Inc. (AMD). · Advanced Micro Devices, Inc. (AMD)
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
May 30, 2026Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang +6Cross-Modal Knowledge Distillation VLM Distillation
Korea Advanced Institute of Science and Technology (KAIST) · University of Illinois Urbana-Champaign (UIUC) · Microsoft Research Asia (MSRA)
DeepLatent: Think with Images via Parallel Latent Visual Reasoning
May 30, 2026Dongchen Lu, Zhimo Li, Mao Shu +1Latent Visual Reasoning VLM Reasoning
Baidu Inc. · Peking University
nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving
May 29, 2026Zhiyu Huang, Johnson Liu, Rui Song +13Autonomous Driving Datasets Autonomous Driving Benchmarks
Xuewei · University of California, Los Angeles · 2Motional
VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
May 29, 2026Hengbo Xu, Shengjie Jin, Yanbiao Ma +1Efficient Multimodal Inference Visual Attention
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China.
Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence
May 29, 2026Yuhan Wang, Shuochen Chang, Yalin Feng +8Multi-Agent Collaboration VLM Reasoning
Peking University · Shanghai Jiao Tong University · Nanyang Technological University +2
ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language Models
May 28, 2026Zihu Wang, Karthik Somayaji N. S, Peng LiVisual Reasoning Large Vision-Language Models
University of California, Santa Barbara
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
May 28, 2026Xiaona Zhou, Muntasir Wahed, Tianjiao Yu +2Interpretable Anomaly Detection Anomaly Localization
University of Illinois Urbana-Champaign · Sandia National Laboratories
Unveiling the Visual Counting Bottleneck in Vision-Language Models
May 28, 2026Xingzhou Pang, Yifan Hou, Junling Wang +1Object Counting Latent Visual Reasoning
Department of Computer Science, ETH Zürich
FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
May 28, 2026Leqi Zhu, Junyan Ye, Kaiqing Lin +3Explainable Deepfake Detection CoT Reasoning
Shanghai AI Lab · Nanjing University · Sun Yat-Sen University +3
Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
May 28, 2026Yaowu Fan, Tao Han, Dazhao Du +2Tool-Using Vision-Language Agents VLM Reasoning
Sun Yat-sen University · HKUST · Harbin Institute of Technology
World Models in Words: Auditing Physical State-Transition Commitments in Vision-Language Models
May 28, 2026Emmanuelle BourigaultVLM Evaluation VLM Reasoning
University of Oxford
On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training
May 28, 2026Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang +1Supervised Fine-Tuning Vision-Language Models
University of California, Los Angeles
CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials
May 28, 2026Chengliang Xu, Xiaogang Li, Peiyao Xiao +3VLM Evaluation Materials Science
Alibaba Group, Beijing, China
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
May 27, 2026Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit +1VLMs for Autonomous Driving Autonomous Driving Safety Evaluation
University of Massachusetts Amherst · Qualcomm
The Abstraction Gap in Vision-Language Causal Reasoning
May 27, 2026Chinh Hoang, Mohammad Rashedul HasanVLM Evaluation Causal Reasoning in Language Models
Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, Nebraska, USA.
Self-Prophetic Decoding to Unlock Visual Search in LVLMs
May 27, 2026Zhendong He, Qiyuan Dai, Guanbin Li +2Large Vision-Language Models VLM Reasoning
School of Computer Science and Engineering, Sun Yat-sen University · ShanghaiTech University
Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
May 27, 2026Yang Zhang, Xiaoshuai Sun, Rui Zhao +5Active Perception Multimodal Reasoning
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China. · Sino-Russian ResearchCenter for Digital Economy. · School of Informatics, Xiamen University, China. +2
MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram Parsing
May 27, 2026Chuang Tang, Chenhao Lin, Yin Xu +5VLM Reasoning Multi-Agent Reasoning
University of Science and Technology of China Hefei, China
Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning
May 27, 2026Xuanzhao Dong, Wenhui Zhu, Peijie Qiu +11Visual Question Answering Tool-Using Vision-Language Agents
Arizona State University, Tempe, AZ, USA · Washington University in St. Louis, St. Louis, MO, USA · Clemson University, Clemson, SC, USA +3
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
May 27, 2026Guannan Lv, Ren Nie, Hongjian Dou +1Multimodal Grounding Efficient Multimodal Inference
Kuaishou Technology

Jun 2, 2026, cs.CVJ/K move · Enter open · S save

Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy

Soohyun Lee, Jaeyoung Kim, Seokhyeon Park, Sihyeon Lee+4

Seoul National University · MADI Co., Ltd. · Hankuk University of Foreign Studies+1

VLM Evaluation Data Visualization Vision-Language Models VLM Reasoning Chart Understanding

Open paper AskPDF arXiv

Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over visual evidence or factual priors learned during training. Current evaluations mix these two sources, obscuring when correct visual interpretation is overridden by memorized facts. We present a framework that isolates visual correctness from factual correctness, revealing validity limitations in existing visualization literacy assessments. Across three experiments with 15 state-of-the-art LVLMs: (1) several models reach human-level performance on standard tests (VLAT), but this may reflect factual recall rather than visual understanding, while randomized-data tests (reVLAT) underestimate literacy when correct visual interpretation is superseded by factual priors. (2) Using our Counterfactual Visualization Literacy Assessment Test (CVLAT) with capability-normalized arbitration metrics, we classify models by the sign of their visual-factual reliance index (VFRI), revealing a visualization-oriented majority and a factual knowledge-oriented minority, though several near-zero cases warrant caution. A human baseline (N=30) on the same counterfactual items confirms that people overwhelmingly follow the chart under conflict, providing a human reference point. (3) Prompt-based intervention can shift prioritization, but its effectiveness is highly model-dependent and direction-asymmetric, and high chart-reading capability does not predict prompt-controllability. Overall, high visualization accuracy is not sufficient evidence of faithful visual reasoning: reliable integration into visual analytics requires evaluating not only visualization literacy but also how models arbitrate between visual evidence and factual priors when the two diverge. Benchmark and code: https://github.com/JaeyoungKim-HCIL/CVLAT

Momentum

Related topics

Latest papers 541