VLM Reasoning

VLM: Vision-Language Model

This field studies how models connect images or video with language to solve tasks involving spatial relations, time, causality, diagrams, and action. Common approaches include chain-of-thought prompting, visual tools and retrieval, structured representations such as scene graphs, and fine-tuning with process-level rewards. Benchmarks increasingly test whether answers and intermediate steps are grounded in visual evidence, including in multi-image, video, scientific, and embodied settings. A central tension is that longer reasoning can help on complex tasks but can also weaken visual grounding, amplify language-based shortcuts, or produce explanations that do not reflect how an answer was reached.

Latest papers

853 papers96 papers in the last four weeks, up 48% on the four weeks before. 0.6% of all new papers.

Reason or Recite: Complementary Specialists with an LLM Judge for Traffic Anomaly Reasoning
Oct 26, 2026Mayur KulkarniVideo Reasoning VLM Reasoning
Stellarview AI, Pune, India
RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction Extraction from Scientific Literature
Oct 23, 2026Jiaxing Sun, Junyuan Gao, Ruikang Zhang +16Multimodal Dataset Document Information Extraction
Shanghai Artificial Intelligence Laboratory · Peking University · South China Normal University +7
$Ψ$ -0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model
Oct 23, 2026Khai Loong Aw, Klemen Kotar, Baihan Zhang +5VLM Reasoning World Models for VLA Models
Stanford University
Separating Angular Alignment from Radial Ordering in Hyperbolic Vision-Language Models
Oct 23, 2026Mingyang Gao, Yuwei Wu, Shiyu Luo +8Vision-Language Models Hyperbolic Representation Learning
Beijing Institute of Technology · Shenzhen MSU-BIT University
OpenHome: From Perception to Insight in Smart-Home Camera Videos
Oct 22, 2026Xianglong Wang, Neil Rodrigues, Pei Guo +9Video Understanding VLM Reasoning
Wyze Labs
ReCoG: Relational Concept Graph for Training-Free Personalization
Oct 22, 2026Changseon Yu, Hyeokjun KweonRetrieval-Augmented Classification VLM Reasoning
GSAIM, Chung-Ang University
Where Did the Light Come From? Diagnosing Cast-Shadow Reasoning in VLMs and Borrowing the Missing Shadow Prior from Image Generation Models
Oct 22, 2026Ryugo Morita, Shunsuke Kitada, Stanislav Frolov +5VLM Reasoning Physical Reasoning
DFKI, Germany · RPTU Kaiserslautern-Landau, Germany · Hosei University, Japan
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Oct 19, 2026Yu Zhou, Cheng-Fu Yang, Rui Sun +8Tool Use in VLMs Multimodal Reasoning
University of California, Los Angeles · Apple
TempoMoE: Identifying and Steering Fast-Slow Thinking Experts for Efficient Multimodal Reasoning
Oct 19, 2026Xiyue Zhang, Keru Zhou, Ziyi Wang +2Mixture-of-Experts Inference Efficient Multimodal Inference
Zhejiang University · Tsinghua University · Wenzhou Business College
Visual Scaffolding: Toward Native Multimodal Reasoning
Oct 18, 2026Run Shao, Zhaoyang Zhang, Ziyu Li +6Multimodal Reasoning VLM Reasoning
Central South University
Video-Language Entailment for Video Similarity Estimation
Oct 17, 2026Benedetta Liberatori, Lorenzo Vaquero, Elisa Ricci +1VLM Reasoning
University of Trento · Fondazione Bruno Kessler
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
Oct 15, 2026Luozheng Qin, Yuhan Zhu, Changhai Zhou +10Spatial Reasoning in Language Models Visual Spatial Reasoning
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
Oct 15, 2026Dongjie Cheng, Ruifeng Yuan, Ran Wei +3VLM Reasoning Video Reasoning
The Hong Kong Polytechnic University · Hangzhou Diagens Biotechnology Co., Ltd
Learning to Think and Explore in 3D World
Oct 15, 2026Yijiang Li, Bingyang Wang, Nuno VasconcelosVLM Reasoning 3D VQA
University of California San Diego · Georgia Institute of Technology
MYOPIA: Understanding the Limits of Tree-Based Reasoning in Vision-Language Models
Oct 15, 2026Islam Mesabah, Sary Elmansoury, Gerrit Großmann +2VLM Reasoning VLM Evaluation
German Research Centre for Artificial Intelligence (DFKI), Kaiserslautern, Germany
Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs
Oct 15, 2026Zeyuan Yang, Zhuohao Chen, Jiaben Chen +3Attention-Guided Distillation RL for VLMs
UMass Amherst · UIUC · MIT
AdaLoop: Thinking with the Vision Encoder
Oct 15, 2026Xinran Nicole Han, Yiyang Lu, Katelyn Gan +1VLM Reasoning Visual Reasoning
Harvard University · MIT
Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models
Oct 14, 2026Frank F. Yang, Kefei Yan, Yiren Wang +1VLM Distillation On-Policy Distillation
Georgia Institute of Technology, Atlanta, GA, USA
Probing Negation Understanding in Vision-Language Models With Object Attention
Oct 14, 2026Beth Pearson, Michael Wray, Martha LewisVLM Reasoning VLM Evaluation
University of Bristol · ILLC, University of Amsterdam
DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning
Oct 14, 2026Qihang Cao, Haoyuan Li, Zihan Guo +8Spatiotemporal Reasoning Spatial Reasoning
1Nanyang Technological University · 2Shenzhen campus of Sun Yat-sen University · 3Yinwang Intelligent Technology Co. Ltd +1
Write Once, Plan Many: Building Reusable Visual Planning Systems from One Scene
Oct 13, 2026Ruixiao Yang, Yilun Hao, Mingxin Yu +2Program Synthesis Model-Based Planning
MIT · MIT-IBM Watson AI Lab
Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?
Oct 13, 2026Juntong Feng, Qingan Liu, Jingru Dong +8VLM Reasoning VLMs for Robotics
Dalian University of Technology · Nanyang Technological University
Segment Where You Look: Attention as the Interface Between Language Models and Segmenters
Oct 13, 2026Eslam Abdelrahman, Hamza Omar Alkaf, Yuheng Li +5Vision-Language Models Referring Expression Segmentation
King Abdullah University of Science and Technology (KAUST) · Adobe Research
GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models
Oct 13, 2026Rong Li, Shijie Li, Jiangyong Huang +7Geospatial QA Visual Spatial Reasoning
The Hong Kong University of Science and Technology (Guangzhou) · Beijing Institute for General Artificial Intelligence · Agency for Science, A*STAR +3
CREATE: Creativity Evaluation of VLMs using the Visual Remote Associates Test
Oct 13, 2026Ziqing Yang, Anubhav Jangra, Smaranda MuresanVLM Evaluation VLM Reasoning
Columbia University, USA · Barnard College, Columbia University, USA
Know-Thy-Not: Training-Free Targeted Negation in Dual-Encoder Vision-Language Models
Oct 12, 2026DoYoung Kim, Changkyu Choi, Adín Ramírez Rivera +2Vision-Language Models VLM Reasoning
Sungkyunkwan University, South Korea · University of Oslo, Norway
Geometric Parrots: Rule Absence vs. Rule Fragility in Spatial and Physical Reasoning for Vision-Language Models
Oct 12, 2026Bilal Jawaid, Hamza Hanif, Muhammad Maaz Uddin +8Sycophancy in VLMs VLM Reasoning
Independent Researcher · Simon Fraser University, Canada · Salim Habib University, Karachi, Pakistan +7
Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning
Oct 11, 2026Fan Yang, Lifeng Chen, Yipu Wang +14VLM Reasoning Multimodal CoT Reasoning
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Beijing Jiaotong University +4
A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning
Oct 11, 2026Hao Li, Wenping Yin, Fabian Deuser +5Geospatial Reasoning VLM Reasoning
Department of Geography, National University of Singapore, Singapore · College of Geodesy and Geomatics, Shandong University of Science and Technology, China · University of the Bundeswehr Munich, Germany +6
HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning
Oct 10, 2026Yiming Zhang, Enzhi Zhou, Junan Lin +4Human Motion Understanding VLM Reasoning
Nanyang Technological University, Singapore · Ant Group, Hangzhou, China

Oct 26, 2026J/K move · Enter open · S save

Reason or Recite: Complementary Specialists with an LLM Judge for Traffic Anomaly Reasoning

Mayur Kulkarni

Stellarview AI, Pune, India

Video Reasoning VLM Reasoning Traffic Anomaly Detection

Open paper AskPDF arXiv

Road anomalies such as collisions, violations, and sudden hazards demand more from video understanding than detection: a practical system must verify what happened, describe the scene, and explain the cause. We find these competences pull in opposite directions for vision-language models: closed-form questions reward precise, evidence-grounded reasoning, while open-ended answers are scored by similarity to reference text, where matching the annotation style matters as much as reasoning correctly. We present Reason-or-Recite (RoR), a two-specialist framework for the Traffic Anomaly Reasoning track of the 2026 AI City Challenge. RoR (1) rewrites the official chain-of-thought annotations into a structured, temporally grounded schema and LoRA-tunes a 9B vision-language model on the enhanced traces; (2) fine-tunes a 4-bit-quantized 27B model on answers alone, absorbing the annotation style; and (3) selects between the two candidates per question with a training-free LLM judge. RoR ranks first on the in-domain leaderboard with mean score 0.6788.