Reasoning for VLMs

VLM: Vision-Language Model

Follow this topic Ask about this topic

Latest papers

78 papers31 papers in the last four weeks, up 933% on the four weeks before. 0.2% of all new papers.

Tinted Frames: Question Framing Blinds Vision-Language Models
Mar 19, 2026Wan-Cyuan Fan, Jiayun Luo, Declan Kutscher +2Vision-Language Models VLM Robustness
University of British Columbia · Vector Institute for AI · University of California, Berkeley
TAU-R1: Visual Language Model for Traffic Anomaly Understanding
Mar 19, 2026Yuqiang Lin, Kehua Chen, Sam Lockyer +12Reasoning for VLMs Traffic Anomaly Detection
University of Bath, BA2 7AY, United Kingdom · University of Washington, WA 98105, USA · City of Carmel, Indiana, USA +1
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Mar 17, 2026Shenzhi Wang, Shixuan Liu, Jing Zhou +8Reasoning for VLMs VLM Reasoning
Qwen Team, Alibaba Inc. · LeapLab, Tsinghua University
The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models
Mar 17, 2026Robert Welch, Emir Konuk, Kevin SmithConfidence Estimation for VLMs VLM Reasoning
KTH Royal Institute of Technology, Stockholm, Sweden · Science for Life Laboratory, Stockholm, Sweden
Multi-turn Physics-informed Vision-language Model for Physics-grounded Anomaly Detection
Mar 16, 2026Yao Gu, Xiaohao Xu, Yingna WuReasoning for VLMs Video Anomaly Detection
Shanghaitech University · University of Michigan, Ann Arbor
Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning
Mar 13, 2026Selim Furkan Tekin, Yichang Xu, Gaowen Liu +3VLM Hallucination Mitigation VLM Reasoning
Georgia Institute of Technology · Cisco Systems
Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
Feb 26, 2026Amita Kamath, Jack Hessel, Khyathi Chandu +3VLM Reasoning Reasoning for VLMs
University of Washington · University of California, Los Angeles · Samaya AI +2
MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving
Feb 25, 2026Lingjun Zhang, Yujian Yuan, Changjie Wu +7Reasoning for VLMs VLMs for Autonomous Driving
Amap, Alibaba Group · The Hong Kong University of Science and Technology · The Chinese University of Hong Kong +1
Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning
Feb 18, 2026Mingjia Shi, Yinhan He, Yaochen Zhu +1VLM Reasoning Reasoning for VLMs
University of Virginia.
CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving
Feb 17, 2026Lucas Elbert Suryana, Farah Bierenga, Sanne van Buuren +6Reasoning for VLMs VLM Reasoning
Department of Transport & Planning, Faculty of Civil Engineering and Geosciences, Delft University of Technology · Centre for Meaningful Human Control, Delft University of Technology · Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands +1
Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
Feb 9, 2026Siqu Ou, Tianrui Wan, Zhiyuan Zhao +2Reasoning for VLMs Attention Intervention in VLMs
TeleAI · Shanghai Jiao Tong University · Northwestern Polytechnical University
Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design
Jan 1, 2026Omar Sharif, Eftekhar Hossain, Nikhil Singh +1Reasoning for VLMs Vision-Language Models
Department of Computer Science, Dartmouth College · Department of Computer Science, University of Central Florida · Independent Researcher
Understanding the Effects of Distractors on Reasoning Vision-Language Models
Nov 26, 2025Jiyun Bae, Hyunjong Ok, Sangwoo Mo +1VLM Reasoning Visual Question Answering
Pohang University of Science and Technology (POSTECH)
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models
Oct 24, 2025Hoang Phan, Xianjun Yang, Yuanshun Yao +6RL Post-Training Catastrophic Forgetting
Meta Superintelligence Labs · New York University · Johns Hopkins University
VRPRM: Process Reward Modeling via Visual Reasoning
Aug 5, 2025Xinquan Chen, Chongying Yue, Bangwei Liu +3Process Reward Models Multimodal Reward Modeling
Shanghai AI Laboratory · Zhejiang University · East China Normal University
Position: Reasoning After Perception Means Reasoning Without Vision
Jul 21, 2025Hongcheng Gao, Zihao Huang, Jingyi Tang +12Multimodal Understanding Visual Reasoning
Tsinghua University · BIT · Peking University +6
Towards General Continuous Memory for Vision-Language Models
May 23, 2025Wenyi Wu, Zixuan Song, Kun Zhou +3Memory-Augmented VLMs Reasoning for VLMs
University of California, San Diego.
Human-centered evaluation of data visualization understanding in vision-language models
May 22, 2025Arnav Verma, Kushin Mukherjee, Christopher Potts +2VLM Evaluation Chart Understanding
Department of Psychology at Stanford University · Department of Linguistics at Stanford University · Department of Communication at University of California, Los Angeles

Mar 19, 2026J/K move · Enter open · S save

Tinted Frames: Question Framing Blinds Vision-Language Models

Wan-Cyuan Fan, Jiayun Luo, Declan Kutscher, Leonid Sigal+1

University of British Columbia · Vector Institute for AI · University of California, Berkeley

Vision-Language Models VLM Robustness Visual Evidence Sensitivity in VLMs Reasoning for VLMs Vision-Language Grounding

Open paper AskPDF arXiv

Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of attention applied to visual inputs based on linguistic framing even when alternative framings demand identical visual reasoning. Using visual attention as a probe, we quantify how framing alters both the amount and distribution of attention over the image. Constrained framings, such as multiple choice and yes/no, induce substantially lower attention to image context compared to open-ended, reduce focus on task-relevant regions, and shift attention towards uninformative tokens. We further demonstrate that this attention misallocation is the principal cause of degraded accuracy and cross-framing inconsistency. Building on this mechanistic insight, we introduce a lightweight prompt-tuning method using learnable tokens that encourages the robust, visually grounded attention patterns observed in open-ended settings, improving visual grounding and improving performance across framings.