Visual Reasoning

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

13 new papers

A weekly snapshot of new work published in Visual Reasoning.

Period ending 2026-09-14

6 new papers

A weekly snapshot of new work published in Visual Reasoning.

Period ending 2026-09-07

23 new papers

A weekly snapshot of new work published in Visual Reasoning.

Inside this field

Focused directions

Focused topic

Visual Reasoning

Within Visual Reasoning

252 papersExplore

Focused topic

Visual Evidence

Within Visual Reasoning

148 papersExplore

Focused topic

Visual Representations

Within Visual Reasoning

70 papersExplore

Focused topic

Latent Visual Reasoning

Within Visual Reasoning

48 papersExplore

Focused topic

Visual Context

Within Visual Reasoning

45 papersExplore

528 papers

Latest in Visual Reasoning

Browse all topics →

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
May 29, 2026Qian Kou, Xiaofeng Shi, Yulin Li +4Textvqa Visual Reasoning
StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning
May 29, 2026Xixiang He, Baiqi Wu, Xingming Li +4Visual Reasoning Diagnostic Benchmark
Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidence
May 29, 2026Yuhan Wang, Shuochen Chang, Yalin Feng +8Knowledge-Based Visual Question Answering Multimodal Agents
ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language Models
May 28, 2026Zihu Wang, Karthik Somayaji N. S, Peng LiLatent Visual Reasoning Large Vision Language Models
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
May 28, 2026Yue Zhang, Zun Wang, Han Lin +3Spatial Reasoning Spatial Question Answering
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
May 28, 2026Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9Flow-Matching Vision-Language-Action Vision-Language-Action Models
Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
May 28, 2026Yaowu Fan, Tao Han, Dazhao Du +2Visual Reasoning
Brain-IT-VQA: From Brain Signals to Answers
May 28, 2026Roman Beliy, Matias Cosarinsky, Oliver Heinimann +2Brain Magnetic Resonance Imaging Textvqa
On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training
May 28, 2026Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang +1Large Vision Language Models Visual Reasoning
Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challenge
May 28, 2026Yinsong Xu, Wei Jing, Liuxin Zhang +2Video Understanding Knowledge-Based Visual Question Answering
VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
May 27, 2026Qiaoru Li, Shaotian Liang, Jintao Chen +4Latent Visual Reasoning Efficient Latent Reasoning
Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models
May 27, 2026Corentin Seutin, Mohamed Amine Ettaki, Michaël Clément +2Large Vision Language Models Segmentation Model
When Discourse Pressures Conflict: Information Structure in Vision-Language Model Outputs
May 27, 2026Marcell Fekete, Johannes Bjerva, Tamás KáldiDiscourse Linguistics
Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
May 27, 2026Yang Zhang, Xiaoshuai Sun, Rui Zhao +5Multimodal Reasoning Multimodal Reasoning Benchmarks
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
May 27, 2026Guannan Lv, Ren Nie, Hongjian Dou +1Visual Evidence
Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions
May 26, 2026Antonia Karamolegkou, Nicolas Angleraud, Benoît Sagot +1Optical Character Recognition Ancient Greek
Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models
May 26, 2026Yifan Jiang, Dae Yon Hwang, Jesse C. Cresswell +1Chart Visual Reasoning
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
May 26, 2026Qian Yang, Ankur Sikarwar, Huy Le +4Visual Reasoning Unified Multimodal Models
Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models
May 26, 2026Aaron Branson Cigres Li, Zhaowei Wang, Yu Zhao +9Multimodal Retrieval Large Vision Language Models
VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes
May 25, 2026Jingru Chen, Yiming Liu, Mingtao Chen +5Fine-Grained Perception Visual Evidence
EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
May 25, 2026Geo Ahn, Jiwook Han, Youngrae Kim +2Video Temporal Grounding Temporal Grounding
STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
May 25, 2026Yiming Liang, Yixiao Chen, Yiyang Zhou +8Video-Language Models Video Understanding
Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents
May 25, 2026Dong-Hee Kim, Reuben Tan, Donghyun KimVisual Reasoning Visual Analytics
TopoAlign: Topology-Aware Visual Representation Alignment
May 25, 2026Xinyuan Yan, Rita Sevastjanova, Mennatallah El-Assady +1Topological Data Analysis Visual Representations
Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
May 25, 2026Fanhu Zeng, Zhicong Luo, Zefan Wang +3Multimodal Reasoning Visual Reasoning
GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving
May 25, 2026Yingji Zhang, Yong Dai, André FreitasRepresentational Geometry Visual Representations
Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning
May 25, 2026Longteng Guo, Yifan Wang, Pengkang Huo +4Multimodal Reasoning Benchmarks Multi-Modal Large Language Models
ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection
May 24, 2026Huangsen Cao, Hongkang Chu, Yuxi Li +6Synthetic Image Detection Visual Evidence
DUEL: Adversarial Self-Play for Multimodal Reasoning
May 24, 2026Lin Qiu, Hanqing Zeng, Yao Liu +3Visual Reasoning Self-Play
The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench
May 23, 2026Dingling Yao, Andrea Polesello, Adeel Pervez +2Scientific Discovery Perceptual Understanding
Vision-Language Binding in In-Context Image Generation
May 23, 2026Chris Ge, Rohit Gandikota, Antonio Torralba +1Single Images Visual Context
Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
May 23, 2026Wen Ma, Fucheng Niu, Zhiting Fan +3Medical Visual Question Answering Clinical Reasoning
OmniEgo-R $^2$ : A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026
May 23, 2026Zixu Li, Zhiwei Chen, Zhiheng Fu +4Egocentric Video Multimodal Reasoning
Structured Visual Evidence Decomposition for Evidence-Grounded Multimodal Screening of Obstructive Sleep Apnea-Hypopnea Syndrome
May 23, 2026Chen Zhan, Yingchen Wei, Xiaoyu Tan +2Screening Multimodal Clinical Data
Unified 3D Scene Understanding Through Physical World Modeling
May 23, 2026Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh +43D Scene Understanding 3D Representation
ETCHR: Editing To Clarify and Harness Reasoning
May 22, 2026Beichen Zhang, Yuhong Liu, Jinsong Li +3Image Editing Visual Reasoning
Leveraging Foundation Models for Causal Generative Modeling
May 22, 2026Aneesh Komanduri, Xintao WuCausal Foundation Models Causal Reasoning
Point Tracking Improves World Action Models
May 22, 2026Jiarui Guan, Wenshuai Zhao, Yue Pei +3Efficient World-Action Model Multi-Object Tracking
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
May 22, 2026Mingfang Zhang, Jingjing Pan, Ashutosh Kumar +7Video Temporal Grounding Visual Evidence
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
May 21, 2026Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei +3Visual Reasoning Large Vision Language Models
Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?
May 21, 2026Zixuan Lan, Luzhe Sun, Matthew R. Walter +1Large Vision Language Models Explicit Visual Grounding
Action with Visual Primitives
May 21, 2026Weilong Guo, Yuchen Wang, Renping Zhou +5Visual Representations
LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
May 21, 2026Xiaodong Mei, Diankun Zhang, Hongwei Xie +3Efficient Vision-Language-Action Models Autonomous Driving
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
May 21, 2026Changyuan Tian, Zhicong Lu, Huaxing Liu +7Multimodal Reasoning Multimodal Learning
COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition
May 21, 2026Junhyub Lee, Seunghun Chae, Hyosu KimLarge Vision Language Models Visual Representations
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
May 21, 2026Yifan Dai, Zhenhua Wu, Bohan Zeng +18Audio-Visual Reasoning Omni-Modal
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
May 21, 2026Shiqi Huang, Ziyue Wang, Zhongrong Zuo +3Self-Evolution Visual Reasoning
MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks
May 21, 2026Han Zhang, Wanting Jiang, Tomasz Kornuta +2Agentic Video Generation Large Vision Language Models
Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
May 20, 2026Tianyi Zhang, Mahtab Bigverdi, Ranjay KrishnaLatent Reasoning Tokens Vision-Language
Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
May 20, 2026Yicheng Jiang, Jiaxu Wang, Junhao He +8Latent Representation Differentiable Rendering
Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
May 20, 2026Yutong Xie, Zhenglin Hua, Ran Wang +3Large Language Model Hallucination Large Vision Language Models
Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
May 20, 2026Lena Wild, Katie Z Luo, Marco PavoneLane Geometry Large Vision Language Models
VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering
May 20, 2026Jiayi Chen, Benteng Ma, Zehui Liao +3Robust Hallucination Detection Medical Visual Question Answering
SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction
May 20, 2026Miaobo Hu, Shuhao Hu, Bokun Wang +5Visual Evidence Relation Extraction
VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
May 20, 2026Mozhgan Nasr Azadani, Yimu Wang, Yongpeng Zhu +5Explicit Visual Grounding Visual Evidence
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
May 19, 2026Juncheng Wu, Hardy Chen, Haoqin Tu +6Large Vision Language Models Visual Reasoning
LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition
May 19, 2026Jiaxin Wang, Muwei Jian, Hui Yu +2Facial Expression Recognition Vision-Language
Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting
May 19, 2026Yue Yu, Haibo Chen, Shuo Chen +2Text-To-Image Creativity
CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
May 19, 2026Pengcheng Wang, Haoxiang Liu, Yang Dai +5Captcha-Capable Native Graphical User Interface Agent Visual Reasoning
JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA
May 19, 2026Hyunju Kang, Woohyun Lee, Jaewon Kim +1Multimodal Reasoning Visual Reasoning

May 29, 2026 · cs.CVJ/K move · Enter open · S save

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding

Qian Kou, Xiaofeng Shi, Yulin Li, Xiaosong Qiu+3

Multimodal Large Language Models (MLLMs) have demonstrated significant achievements in general visual question answering (VQA) tasks. However, they remain brittle on mechanical engineering drawings, where high annotation density and weak domain knowledge, compounded by unreliable spatial relation reasoning under strict projection rules and geometric constraints, make decisive cues easy to miss and frequently lead to wrong answers. To bridge this gap, we introduce the first comprehensive mechanical drawing understanding dataset, MechVQA, created through a semi-automated construction and quality-control pipeline. MechVQA contains 3.3k high-density pictures with 21K question-answer pairs, spanning 10 different fine-grained tasks across three capability levels: Recognition, Reasoning, and Judging, providing a testbed to evaluate and improve MLLM understanding on real-world mechanical drawings. On top of MechVQA, we then develop the MechVL model through a multi-stage training paradigm, building a strong domain-specialized baseline. Extensive experimental results demonstrate that MechVL outperforms the strongest closed-source baseline by 7.57 percentage points on the MechVQA total score, significantly enhancing mechanical drawing understanding ability and providing a reusable foundation for deploying MLLMs in mechanical design and inspection scenarios.

Textvqa Visual Reasoning Computer-Aided Design Question-Answer Pairs

Open paper Ask about it PDF