Reasoning for VLMs

VLM: Vision-Language Model

Latest papers

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

Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
Nov 6, 2026Hongbin Lin, Sizhe Zou, Juangui Xu +6Reasoning for VLMs VLM Reasoning
The Hong Kong University of Science and Technology (Guangzhou) · CISPA Helmholtz Center for Information Security · The Chinese University of Hong Kong +2
PSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic Reasoning
Nov 5, 2026Qingyun Liu, Yuankun Liu, Jiaye Feng +6Scene Graph Generation Tool-Using Vision-Language Agents
Peking University Beijing, China · AlignBase Beijing, China
Benchmarking Fine-Grained Visual Reasoning for Remote Sensing in Urban Management
Nov 4, 2026Jiawei Zhang, Rizhao Cai, Dayan GuanRemote Sensing Image Understanding Reasoning for VLMs
School of Electronics and Information Engineering, Harbin Institute of Technology, 150000 Harbin, China. · Huawei International PTE LTd, 486066 Singapore, Singapore.
How Do Artificial Agents Make Decisions in Light of Visual Data?
Nov 3, 2026Keyty Loza, Shayan MonadjemiReasoning for VLMs Data Visualization
Lamar University · Oak Ridge National Laboratory
Learning Where to Look: Observation Policy Optimization for Thinking with Images
Nov 3, 2026Junfeng Wang, Jiawei Liu, Yongchao Xu +5Visual Question Answering Reasoning for VLMs
University of Science and Technology of China · Alibaba Group
FlowBench: Counterfactual Imagination Training for Spatial Intelligence
Nov 2, 2026Yifan Liu, Baihan Zhang, Khai Loong Aw +2Spatial Reasoning in Language Models Reasoning for VLMs
Stanford University
MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
Nov 2, 2026Zhihan Yin, Jianxin Liang, Yifeng Yao +5Reasoning for VLMs VLM Robustness
Peking University · ByteDance · Wangxuan Institute of Computer Technology +1
Reconstruction as Spatial Evaluation: Diagnosing Cross-View Spatial Intelligence in Large Vision-Language Models
Nov 1, 2026Junfei Wu, Qiuyue Wang, Xuhong Huang +8Spatial Reasoning Benchmarks Multimodal Spatial Reasoning
NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences · Alibaba Token Hub, Alibaba Group · The University of Hong Kong +2
Knowledge-Guided Floodwater Level Reasoning for Cloud-Edge Collaborative Monitoring
Nov 1, 2026Zhengshu Zhou, Shaoyu Wang, Ziyi Geng +2Reasoning for VLMs Edge-Cloud Collaborative Inference
College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China · School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, China
See, Think, Use: Diagnosing Perception and Reasoning Failures in VLMs
Nov 1, 2026Jiacheng Ding, Yanliang Qi, Cong Guo +1VLM Evaluation Reasoning for VLMs
University of Memphis · National University of Singapore
Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Driving QA
Oct 31, 2026T N Rickesh, Pranav Vinodh, Sowmya Kamath SVLM Reasoning Visual Question Answering
natkal · National Institute of Technology Karnataka
When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
Oct 30, 2026Hao Yin, Tianchen Guo, Heming Du +3Reasoning for VLMs Visual Spatial Reasoning
The University of Queensland, Australia · Australian Artificial Intelligence Institute University of Technology Sydney, Australia · Australian Institute for Machine Learning Adelaide University, Australia
SelfThinker: Self-Evolving Reasoning via Reliability-Verified Intrinsic Visual Thoughts
Oct 29, 2026Zhangquan Chen, Ruqi HuangReasoning for VLMs Vision-Language Models
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, Guangdong, China.
Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding
Oct 29, 2026Hongyu Bai, Jiaqi Zeng, Chunzheng ZhuMedical VLMs Reasoning for VLMs
Shanghai Jiao Tong University Shanghai, China · Hunan University Changsha, China
Look at Where You Think: Localization-Head Alignment for Fine-Grained Perception in Thinking VLMs
Oct 29, 2026Yuan Wang, Wei Wu, Hongning WangFine-Grained Visual Perception Reasoning for VLMs
Department of Computer Science and Technology, Tsinghua University · Ant Group
Where Do Vision Language Models Fail at 3D Reasoning?
Oct 29, 2026Khai Le-Duc, Nguyen Kim Hai Bui, An Ngo +11Counting in VLMs Reasoning for VLMs
OneScene-Bench: Do Vision-Language Models Integrate Evidence Across Views?
Oct 28, 2026Swathi Suhas, Anurag Das, Bernt Schiele +1VLM Evaluation Reasoning for VLMs
Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany
V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
Oct 27, 2026Miso Choi, Daekeun Kim, Eunji Kim +1Memory-Augmented VLMs Efficient VLM Inference
Korea University · Amazon
A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs
Oct 27, 2026Alexa R. Tartaglini, Zhengxuan Wu, Thaddäus Wiedemer +3Emergent Communication VLM Interpretability
Google DeepMind · Stanford University
PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds
Oct 26, 2026Jinyuan Hu, Yilei Jiang, Chen Tang +3Reasoning for VLMs Causal Reasoning
MMLab, The Chinese University of Hong Kong
Of Chains and Gains: What Reinforcement Learning changes on Reasoning-based Image Quality Assessment
Oct 23, 2026Yixuan Li, Yuxuan Jiang, Hanwei Zhu +4Image Quality Assessment Reinforcement Learning with Verifiable Rewards
University of Bristol, UK · Jiangxi University of Finance and Economics, China · China University of Mining and Technology, China +1
Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images
Oct 23, 2026Somraj Gautam, Gaurav HaritVisual Question Answering Reasoning for VLMs
IIT Jodhpur, Rajasthan, India.
From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning
Oct 23, 2026Yuhang Han, Dingning Liu, Yujie Chen +7RL for VLMs Step-Level Credit Assignment in RL
The Hong Kong University of Science and Technology (Guangzhou) · Shanghai Jiao Tong University · Shadoweave +2
PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models
Oct 23, 2026Junxin Wang, Yingfeng Luo, Xiangchen Song +12Reasoning for VLMs Multimodal Reasoning
School of Computer Science and Engineering, Northeastern University, Shenyang, China · University of Michigan, Ann Arbor, US · Kunming University of Science and Technology, Kunming, China +1
RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
Oct 22, 2026Zhaolu Kang, Tailong Luo, Chenxin Li +13Reasoning for VLMs Visual Evidence Sensitivity in VLMs
Peking University · Chengdu Minto Tech
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
Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning
Oct 21, 2026Wen Ye, Ailin Deng, Zirui Wang +8Reasoning for VLMs Vision-Language Models
Meta Superintelligence Labs · University of Southern California · University of California, Berkeley +2
Asking What a Director Sees Can Change What Vision-Language Models Choose
Oct 21, 2026Jiaxuan Guo, Xingyu Ren, Kejia Zhang +3Reasoning for VLMs
Stanford University · The Chinese University of Hong Kong · University of Maryland, College Park
Beyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal Reasoning
Oct 20, 2026Wei Cai, Jian Zhao, Yuchen Yuan +1Hybrid Language Models Parallel Reasoning in Language Models
Peking University · Institute of Artificial Intelligence (TeleAI), China Telecom
VisualEvolve: A Skill Self-Evolution Framework for Visual Reasoning
Oct 20, 2026Jiawei Wang, Yucun Li, Xueqi Li +9Tool Use in VLMs Reasoning for VLMs
National University of Singapore · Hunan University · Shenzhen University +4

Nov 6, 2026J/K move · Enter open · S save

Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning

Hongbin Lin, Sizhe Zou, Juangui Xu, Xinyue Xu+5

The Hong Kong University of Science and Technology (Guangzhou) · CISPA Helmholtz Center for Information Security · The Chinese University of Hong Kong+2

Reasoning for VLMs VLM Reasoning RL for VLMs Efficient VLM Inference Offline RL

Open paper AskPDF arXiv

Reasoning traces improve vision-language models on complex multimodal tasks, but forcing every input to follow a long reasoning process leads to overthinking and unnecessary inference cost. We study adaptive fast/slow thinking for VLMs, where one model answers directly for simple inputs and reasons step by step when needed. Fast answers and slow traces often come from distinct behavior policies, making a single-reference offline objective misweight one mode. We propose DUAL-REFERENCE BOLT (DR-BOLT), which distinguishes the desired fast/slow mixture reference from the sampling distribution and corrects their mismatch in reward-weighted training. Fast/slow partition competition explains routing in the optimal target; an efficient source-wise correction approximates the exact objective when response formats are well separated. Matched Qwen3-VL comparisons use identical candidate banks to isolate the objective from slow-teacher quality. DR-BOLT improves score-length trade-offs over the evaluated offline and online baselines on ScienceQA and three held-out transfer benchmarks, with a 24.1% cross-benchmark slow ratio and a 2.90-fold end-to-end training speedup over reproduced GRPO. These results support adaptive reasoning in the studied two-reference setting, while broader robustness remains open. Our code is available at https://github.com/HongbinLin3589/DR-BOLT.