RL for VLMs

RL: Reinforcement Learning · VLM: Vision-Language Model

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 227% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 287

All topics

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
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
May 27, 2026Minki Kang, Shizhe Diao, Ryo Hachiuma +4Multimodal Reasoning Agentic Reasoning
1NVIDIA · 2KAIST
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
May 27, 2026Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang +13Image Captioning Object Hallucination in VLMs
1Tsinghua Shenzhen International Graduate School · 2Harbin Institute of Technology, Shenzhen · 3Chinese Academy of Sciences +1
ABot-OCR Technical Report
May 27, 2026Kaitao Jiang, Ruiyan Gong, Xiaolong Cheng +3Vision-Language Models Document Parsing
AMAP CV Lab Alibaba Group
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
Touch-R1: Reinforcing Touch Reasoning in MLLMs
May 26, 2026Yingxin Lai, Yafei Zhou, Fucai Zhu +2Tactile Sensing Multimodal Large Language Models
1Xiamen University · 5Daimon Robotics · 2Great Bay University +2
Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
May 26, 2026Heng Qu, Yike Liu, Renren Jin +4VLM Evaluation Vision-Language Navigation
1Wuhan University · 2Xiaomi
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
May 26, 2026Peng Zhang, Guanghao Zhang, Wanggui He +10Multimodal Large Language Models Video Reasoning
Zhejiang University · Alibaba Group
InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
May 26, 2026Zhiwei Ning, Wenwen Tong, Xiangli Kong +12Multimodal Reasoning VLM Reasoning
Shanghai Jiao Tong University · SenseTime Research · Shandong Normal University
ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
May 25, 2026Jiangyang Li, Cong Wan, Changjie Wu +8Visual Spatial Reasoning VLM Reasoning
1Xi’an Jiaotong University · 2Amap, Alibaba Group · 4Shenzhen University +1
DUEL: Adversarial Self-Play for Multimodal Reasoning
May 24, 2026Lin Qiu, Hanqing Zeng, Yao Liu +3VLM Robustness VLM Reasoning
Meta AI
B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation
May 22, 2026Mario Markov, Stefan Maria Ailuro, Mohammad Mahdi +2Image Segmentation Reinforcement Learning
INSAIT, Sofia University "St. Kliment Ohridski" · INSAIT, Sofia University “St. Kliment Ohridski”
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
May 21, 2026Changyuan Tian, Zhicong Lu, Huaxing Liu +7Multimodal Large Language Models Multimodal Reasoning
AMAP, Alibaba Group · University of Chinese Academy of Sciences · Tsinghua University +1
Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
May 21, 2026Dazhao Du, Jian Liu, Jialong Qin +7Counterfactual Evaluation Video-Language Models
Hong Kong University of Science and Technology · Tencent
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
May 21, 2026Shiqi Huang, Ziyue Wang, Zhongrong Zuo +3Vision-Language Models Video Reasoning
School of Electrical and Electronic Engineering, Nanyang Technological University · ByteDance
Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming
May 20, 2026Yue Zhou, Erxuan Wu, Yikang Sun +5Visual Question Answering Uncertainty Estimation for VLA Models
Computer Aided Medical Procedures (CAMP), TU Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany · Zhongshan Hospital, Fudan University, China +1
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
May 20, 2026Rongbin Tan, Fangfang Lin, Zhenlong Yuan +10Industrial Anomaly Detection Tool-Using Vision-Language Agents
State Key Lab of Processors, Institute of Computing Technology, CAS
PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
May 19, 2026Peizheng Guo, Jingyao Wang, Changwen Zheng +1Robot Policy Learning Credit Assignment in RL
Institute of Software Chinese Academy of Sciences · University of Chinese Academy of Sciences
ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison
May 19, 2026Tianle Li, Xuyang Shen, Yan Ma +7VLM Evaluation Reward Modeling
1The Chinese University of Hong Kong · 2MiniMax
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
May 19, 2026Tianwei Lin, Zhongwei Qiu, Jie Cao +7Radiology Report Generation Radiology VLMs
Zhejiang University · DAMO Academy, Alibaba Group · Hupan Lab +1
Leveraging Latent Visual Reasoning in Silence
May 18, 2026Dongyao Zhu, Zhen Wang, Xi Xiao +7Visual Spatial Reasoning Latent Visual Reasoning
North Carolina State University · UC, San Diego · University of Alabama at Birmingham +4
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
May 18, 2026Junming Liu, Yuqi Li, Yifei Sun +6VLM Robustness Vision-Language Models
Shanghai Artificial Intelligence Laboratory · The City University of New York · The Chinese University of Hong Kong +3
IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning
May 18, 2026Chenghao Li, Fusheng Hao, Xikai Zhang +5Multimodal Grounding Object Hallucination in VLMs
Hangzhou International Innovation Institute, Beihang University · Shenzhen Institute of Advanced Integration Technology, Shenzhen · Kuaishou Technology +1
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
May 18, 2026Pan Wang, Yihao Hu, Xiujin Liu +3Memory-Augmented VLMs Reward Shaping
Ant Group · University of Science and Technology of China · Westlake University +2
An Efficient Streaming Video Understanding Framework with Agentic Control
May 18, 2026Jinming Liu, Jianguo Huang, Zhaoyang Jia +7Streaming Video Understanding Adaptive Model Routing
1Shanghai Jiao Tong University · 2Eastern Institute of Technology, Ningbo, China · 3Microsoft Research Asia
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
May 18, 2026Xiongbin Wu, Zhihao Luo, Shanzhe Lei +7Reinforcement Learning Group Relative Policy Optimization
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · East China Normal University +2
Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning
May 16, 2026Peng Cui, Boyao Yang, Jun ZhuMultimodal Robustness VLM Reasoning
Dept. of Comp. Sci. & Tech., Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab, Tsinghua University, Beijing 100084, China · Dept. of Automation, Tsinghua University, Beijing 100084, China
OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensics
May 16, 2026Jinjie Shen, Zheng Huang, Yuchen Zhang +7Tool Use in VLMs Image Forgery Detection
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China · Wuhan University, Wuhan, China · Xi’an Jiaotong University +2
Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
May 15, 2026Vaidehi Bagaria, Nikshep Grampurohit, Pulkit VermaReinforcement Learning Neural Network Optimization
Indian Institute of Technology Madras
WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
May 15, 2026Baining Zhao, Jiacheng Xu, Weicheng Feng +13World Model Learning Vision-Language Navigation
Tsinghua University · Shandong University · Manifold AI +2

May 28, 2026, cs.CLJ/K move · Enter open · S save

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training

Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang, Nanyun Peng

University of California, Los Angeles

Supervised Fine-Tuning Vision-Language Models VLM Reasoning RL for VLMs

Open paper AskPDF arXiv

Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a controlled diagnostic framework with two synthetic tasks that disentangle perception from reasoning. Our analysis reveals a consistent perception-reasoning asymmetry: post-training improves reasoning more substantially than perception, though the underlying mechanism differs across training paradigms. For supervised fine-tuning (SFT), this asymmetry stems from token imbalance, with perception occupying a smaller fraction of tokens in chain-of-thought supervision. Reweighting the loss boosts end-to-end performance by up to 18.2 points. For reinforcement learning (RL), the asymmetry instead arises from reward coupling, as outcome rewards correlate more strongly with reasoning than perception. Adding a perception-aware reward improves end-to-end accuracy by up to 6.0 points; when ground-truth perception rewards are unavailable, a reliable surrogate provides useful signal, yielding gains of 2.2 points. Beyond the controlled setting, these strategies also improve real-world visual reasoning, with gains of up to 3.3 points across three benchmarks. Overall, we diagnose the causes of asymmetric optimization and provide actionable guidance that benefits both synthetic and realistic settings.

Momentum

Related topics

Latest papers 287