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

Geo-Strat-RL: Learning Geological Event Reasoning from Verifiable Tasks
Jun 23, 2026Lukas MosserVLM Reasoning Reinforcement Learning with Verifiable Rewards
Aker BP ASA
video-SALMONN-R $^3$ : Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding
Jun 23, 2026Yixuan Li, Guangzhi Sun, Yudong Yang +1Efficient VLM Inference Video QA
Tsinghua University · University of Cambridge
E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis
Jun 22, 2026Sijing Li, Zhongwei Qiu, Zhuoya Wang +6Medical Image Grounding VLM Hallucination Mitigation
Zhejiang University · DAMO Academy, Alibaba Group · Hupan Lab +3
AIR: Adaptive Interleaved Reasoning with Code in MLLMs
Jun 22, 2026Cong Han, Xiaohan Lan, Haibo Qiu +1Multimodal Large Language Models Mathematical Reasoning
1Independent Researcher.
dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
Jun 22, 2026Yuhao Wu, Yitian Liu, Weijie Shen +13Vision-Language-Action Models VLMs for Robotics
ScaleLab at SJTU · 1Shanghai Jiao Tong University · 3Baidu AI Cloud +3
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
Jun 22, 2026Jiho Choi, Seonho Lee, Seojeong Park +1Visual Question Answering Active Perception
Graduate School of Artificial Intelligence, KAIST, Republic of Korea · KRAFTON, Republic of Korea
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
Jun 22, 2026Haoling Li, Kai Zheng, Jie Wu +4Multimodal Reasoning Mathematical Reasoning
1Tsinghua University · 2Tencent Hunyuan
CFPO: Counterfactual Policy Optimization for Multimodal Reasoning
Jun 22, 2026Zhangyuan Yu, Wanran Sun, Guangjing Yang +2Multimodal Reasoning VLM Hallucination Mitigation
Beijing University of Posts and Telecommunications, Beijing, China.
When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR
Jun 20, 2026Zekun XuVision-Language Models Video-Language Models
School of Computer Science, The University of Sydney, Sydney, Australia
CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs
Jun 18, 2026Chengwen Liu, Hao Peng, Jisheng Dang +3Reward Shaping Video Reasoning
School of Information Science and Engineering, Lanzhou University, Lanzhou, China · School of Medical Technology, Beijing Institute of Technology, Beijing, China · School of Computing, National University of Singapore, Singapore
Native Active Perception as Reasoning for Omni-Modal Understanding
Jun 17, 2026Zhenghao Xing, Ruiyang Xu, Yuxuan Wang +8Audio-Visual Understanding Active Perception
1The Chinese University of Hong Kong · †Work done during an internship at Qwen Team, Alibaba Group. · 2Shanghai Jiao Tong University +2
Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs
Jun 16, 2026Chengwen Liu, Zhe Huang, Jisheng Dang +3Multimodal Reward Modeling Video Reasoning
School of Information Science and Engineering, Lanzhou University, Lanzhou, China · Beijing University of Posts and Telecommunications, Beijing, China · Cloud and AI BU, Huawei, Shenzhen, China +1
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Jun 16, 2026Byung-Kwan Lee, Ximing Lu, Shizhe Diao +6Curriculum RL LLM-Guided RL
NVIDIA
PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space
Jun 16, 2026Bochen Yang, Lianlei ShanEfficient VLA Models Latent Visual Reasoning
Imperial College London · Tsinghua University
See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL
Jun 16, 2026Yilian Liu, Sicong Leng, Guoshun Nan +7Multimodal Pretraining Visually Grounded Reasoning
Beijing University of Posts and Telecommunications, China · Nanyang Technological University, Singapore · China Telecom, China
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
Jun 16, 2026Yatai Ji, An-Chieh Cheng, Yang Fu +13Visual Spatial Reasoning 3D Spatial Reasoning
The University of Hong Kong · NVIDIA · University of California, San Diego
Context-Aware RL for Agentic and Multimodal LLMs
Jun 15, 2026Peiyang Xu, Bangzheng Li, Sijia Liu +4Multimodal Grounding Contrastive RL
1Princeton University · 2UC Davis
Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes
Jun 15, 2026Tongyan Fang, Siyuan Huang, Naiyu Fang +6Credit Assignment in RL Robotic RL
1ACE Robotics · 2Shenzhen International Graduate School, Tsinghua University · 3The Chinese University of Hong Kong
Thinking with Visual Grounding
Jun 15, 2026Junkai Zhang, Yihe Deng, Kai-Wei Chang +1Visual Spatial Reasoning Vision-Language Grounding
University of California, Los Angeles
OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing
Jun 14, 2026Zebang Cheng, Shuimu Chen, Boxue Yang +7On-Policy Self-Distillation Multimodal Large Language Models
Shenzhen University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · Tsinghua University +6
Self-Questioning Vision-Language Models: Reinforcement Learning for Compositional Visual Reasoning
Jun 14, 2026Saraswathy AmjithVisual Question Answering Visual Reasoning
Massachusetts Institute of Technology
Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes
Jun 13, 2026Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor +2Social Media Analysis Multimodal Large Language Models
Qatar Computing Research Institute, Doha, Qatar · Qatar University, Doha, Qatar · APAVI.AI, France +1
DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
Jun 13, 2026David Huang, Lianlei ShanEfficient Multimodal Inference Multimodal Reasoning
University of Toronto · Tsinghua University
Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
Jun 13, 2026Dianqiao Lei, Lianlei ShanEfficient Inference Efficient VLA Model Inference
1Tsinghua University, Beijing, China.
CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment
Jun 12, 2026Jiayue Cao, Zhicong Lu, Xuehan Sun +6Multimodal Reward Modeling VLM Reasoning
University of Chinese Academy of Sciences · 2Wuhan University · 3Tsinghua University +1
Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding
Jun 11, 2026Animesh Tripathy, Aswanth KrishnanVLM Evaluation Vision-Language Grounding
QpiAI India Pvt. Ltd.
Efficient Reinforcement for Visual-Textual Thinking with Discrete Diffusion Model
Jun 11, 2026Yoonjeon Kim, Yuhta Takida, Chieh-Hsin Lai +2Multimodal Reasoning RL for Diffusion Models
KAIST · Sony AI · KAIST & AITRICS +1
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
Jun 11, 2026Tingyu Li, Le Zhou, Siyuan Li +5Cross-Modal Alignment Multimodal Reasoning
Shanghai Artificial Intelligence Laboratory · Shanghai Jiaotong University · Zhejiang University +1
Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
Jun 11, 2026Changye Li, Meng Lu, Yi Wu +1Tool Use in VLMs Visual Spatial Reasoning
Tsinghua University · Virginia Tech · NVIDIA
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
Jun 10, 2026Chao Lei, Yanbei Jiang, Markus Hiller +4Visual Spatial Reasoning Reinforcement Learning with Verifiable Rewards
School of Computing and Information Systems The University of Melbourne Melbourne, Australia

Jun 23, 2026, cs.LGJ/K move · Enter open · S save

Geo-Strat-RL: Learning Geological Event Reasoning from Verifiable Tasks

Lukas Mosser

Aker BP ASA

VLM Reasoning Reinforcement Learning with Verifiable Rewards Visually Grounded Reasoning RL for VLMs

Open paper AskPDF arXiv

To evaluate whether vision-language models can reason about geological histories, it is necessary to construct observations for which the underlying process history is known. Furthermore, reasoning over geological histories is not just a question of recognizing visual patterns, but also of understanding temporal and structural relationships that may be only indirectly visible or highly ambiguous. When ground-truth event histories are not uniquely identifiable or are unavailable, it remains an open challenge to teach models capable of visual reasoning to produce valid geological reconstructions that are consistent with both observed evidence and geological principles. We therefore investigate whether defining a verifiable geological reasoning task can improve geological event reconstruction across observation domains through reinforcement learning with verifiable rewards (RLVR). To this end, we present Geo-Strat-RL, a synthetic environment that generates stratigraphic observations and compact visible-evidence event histories. The environment combines a geological generator with an executable verifier that scores chronology, event identity, deposition, and structural relationships. We show that RLVR improves geological reconstruction in vision-language models (VLMs), increasing geological content scores on held out stratigraphic diagrams. We further evaluate the same held-out geological histories in a synthetic seismic observation domain by converting the generated scenes into acoustic-impedance-derived amplitude sections. In this controlled paired-renderer setting, we present evidence that geological reasoning learned from stratigraphic diagram-domain RLVR training transfers to synthetic seismic representations without seismic-specific training examples, supporting the hypothesis that RLVR can teach reusable geological reasoning concepts across related observation formats.

Momentum

Related topics

Latest papers 287