multimodal_r1_papers

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

multimodal_r1_papers

★ 9 Open GitHub ↗

Deepseek RL (GRPO)-Inspired Research for Vision & Multimodal Reasoning

Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Deepseek RL (GRPO)-Inspired Research for Vision & Multimodal Reasoning

This repository maintains a curated and updated collection of research papers and repositories focused on Reinforcement Learning (RL)-inspired methods such as Group Relative Policy Optimization (GRPO) applied to Vision and Multimodal Reasoning tasks.

## Papers

| Date           | Paper                                                                                                                                               | Repository                                                |
|----------------|-----------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------|
| July 2, 2025  | [Kwai Keye-VL Technical Report](https://arxiv.org/abs/2507.01949)  | [Github](https://github.com/Kwai-Keye/Keye)  |
| July 1, 2025  | [GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://arxiv.org/abs/2507.01006)  | [Github](https://github.com/THUDM/GLM-4.1V-Thinking)  |
| June 28, 2025  | [Listener-Rewarded Thinking in VLMs for Image Preferences](https://arxiv.org/abs/2506.22832)  | -  |
| June 27, 2025  | [MiCo: Multi-image Contrast for Reinforcement Visual Reasoning](https://arxiv.org/abs/2506.22434)  | -  |
| June 26, 2025  | [ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models](https://arxiv.org/abs/2506.21356)  | [Github](https://github.com/Vchitect/ShotBench/tree/main)  |
| June 25, 2025  | [MMSearch-R1: Incentivizing LMMs to Search](https://arxiv.org/abs/2506.20670)  | [Github](https://github.com/EvolvingLMMs-Lab/multimodal-search-r1)  |
| June 20, 2025  | [Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?](https://arxiv.org/abs/2506.17417)  | -  |
| June 20, 2025  | [Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens](https://arxiv.org/abs/2506.17218)  | [Github](https://github.com/UMass-Embodied-AGI/Mirage)  |
| June 20, 2025  | [Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs](https://arxiv.org/abs/2506.16962)  | [Github](https://github.com/manglu097/Chiron-o1)  |
| June 19, 2025  | [GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning](https://arxiv.org/abs/2506.16141)  | [Github](https://github.com/TencentARC/GRPO-CARE)  |
| June 16, 2025  | [Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning](https://arxiv.org/abs/2506.13654)  | [Github](https://github.com/egolife-ai/Ego-R1)  |
| June 11, 2025  | [ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs](https://arxiv.org/abs/2506.10128)  | [Github](https://github.com/si0wang/ViCrit)  |
| June 10, 2025  | [VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning](https://arxiv.org/abs/2506.09049)  | [Github](https://github.com/MARS-EAI/VIKI-R)  |
| June 9, 2025  |  [DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO](https://arxiv.org/abs/2506.07464)  |  [Github](https://github.com/mlvlab/DeepVideoR1)  |
| June 4, 2025  |  [Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning](https://arxiv.org/abs/2506.04207)  |  [Github](https://github.com/CSfufu/Revisual-R1)  |
| June 4, 2025  |  [RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics](https://arxiv.org/abs/2506.04308)  |  [Github](https://github.com/Zhoues/RoboRefer)  |
| June 4, 2025  |  [MiMo-VL Technical Report](https://arxiv.org/abs/2506.03569)  |  [Github](https://github.com/XiaomiMiMo/MiMo-VL)  |
| June 2, 2025  |  [SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis](https://arxiv.org/abs/2506.02096)  |  [Github](https://github.com/NUS-TRAIL/SynthRL)  |
| June 2, 2025  |  [SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning](https://arxiv.org/abs/2506.01713)  |  [Github](https://github.com/SUSTechBruce/SRPO_MLLMs)  |
| May 29, 2025  |  [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://arxiv.org/abs/2505.23747)  |  [Github](https://github.com/diankun-wu/Spatial-MLLM)  |
| May 28, 2025  |  [Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO](https://arxiv.org/abs/2505.22453)  |  [Github](https://github.com/waltonfuture/MM-UPT)  |
| May 28, 2025  |  [Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start](https://arxiv.org/abs/2505.22334)  |  [Github](https://github.com/waltonfuture/RL-with-Cold-Start)  |
| May 27, 2025  |  [MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs](https://arxiv.org/abs/2505.21327)  |  [Github](https://github.com/Alpha-Innovator/MME-Reasoning)  |
| May 26, 2025  |  [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://arxiv.org/abs/2505.15966)  |  [Github](https://tiger-ai-lab.github.io/Pixel-Reasoner/)  |
| May 24, 2025  |  [Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models](https://arxiv.org/abs/2505.18536)  |  [Github](https://github.com/Sun-Haoyuan23/Awesome-RL-based-Reasoning-MLLMs)  |
| May 22, 2025  |  [GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning](https://arxiv.org/abs/2505.17022)  |  [Github](https://github.com/gogoduan/GoT-R1)  |
| May 22, 2025  |  [VLM-R^3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought](https://arxiv.org/abs/2505.16192)  |  -  |
| May 22, 2025  |  [SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward](https://arxiv.org/abs/2505.17018)  |  [Github](https://github.com/kxfan2002/SophiaVL-R1)  |
| May 20, 2025  |  [Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning](https://arxiv.org/abs/2505.14677)  |  [Github](https://github.com/maifoundations/Visionary-R1)  |
| May 20, 2025  |  [UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning](https://arxiv.org/abs/2505.14231)  |  [Github](https://github.com/AMAP-ML/UniVG-R1)  |
| May 20, 2025  |  [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://arxiv.org/abs/2505.14460)  |  [Github](https://github.com/TianheWu/VisualQuality-R1)  |
| May 20, 2025  |  [Visual Agentic Reinforcement Fine-Tuning](https://arxiv.org/abs/2505.14246)  |  [Github](https://github.com/Liuziyu77/Visual-RFT/tree/main/Visual-ARFT)  |
| May 17, 2025  |  [VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning](https://arxiv.org/abs/2505.12081)  | [Github](https://github.com/dvlab-research/VisionReasoner)  |
| May 16, 2025  |  [GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning](https://arxiv.org/abs/2505.11049)                                     |  - |
| May 12, 2025  |  [DanceGRPO: Unleashing GRPO on Visual Generation](https://arxiv.org/abs/2505.07818)                                     |  [Github](https://github.com/XueZeyue/DanceGRPO)  |
| May 11, 2025  |  [Seed1.5-VL Technical Report](https://arxiv.org/abs/2505.07062)      |  [Github](https://github.com/ByteDance-Seed/Seed1.5-VL)  |
| May 6, 2025   |  [X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains](https://arxiv.org/abs/2505.03981)           |  [Github](https://github.com/microsoft/x-reasoner)  |
| May 6, 2025   |  [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://arxiv.org/abs/2505.03318)  |  [Github](https://github.com/CodeGoat24/UnifiedReward)  |
| May 5, 2025   |  [R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning](https://arxiv.org/abs/2505.02835)   |  [Github](https://github.com/yfzhang114/r1_reward)   |
| Apr 23, 2025  |  [Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning](https://arxiv.org/abs/2504.16656)                |  [Github](https://github.com/SkyworkAI/Skywork-R1V)  |
| Apr 21, 2025  |  [Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models](https://arxiv.org/abs/2504.15271)  |  [Github](https://github.com/NVlabs/EAGLE)  |
| Apr 21, 2025  |  [VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models](https://arxiv.org/abs/2504.15279)  |  [Github](https://github.com/VisuLogic-Benchmark/VisuLogic-Eval)  |
| Apr 14, 2025  |  [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://arxiv.org/abs/2504.10479)  |  [Github](https://github.com/OpenGVLab/InternVL)  |
| Apr 13, 2025  |  [TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning](https://arxiv.org/abs/2504.09641)  |  [Github](https://github.com/ZhangXJ199/TinyLLaVA-Video-R1)  |
| Apr 10, 2025  |  [VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning](https://arxiv.org/abs/2504.08837)  |  [Github](https://github.com/TIGER-AI-Lab/VL-Rethinker/)  |
| Apr 10, 2025  |  [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://arxiv.org/abs/2504.11468)  |  -  |
| Apr 10, 2025  |  [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://arxiv.org/abs/2504.07615)  |  [Github](https://github.com/om-ai-lab/VLM-R1)  |
| Apr 10, 2025  |  [VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning](https://arxiv.org/abs/2504.07956)                            |  [Github](https://github.com/zhishuifeiqian/VCR-Bench)  |
| Apr 9, 2025 | [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://arxiv.org/abs/2504.06958)                                   |  [Github](https://github.com/OpenGVLab/VideoChat-R1)  |
| Apr 8, 2025  | [Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought](https://arxiv.org/abs/2504.05599)                                                |  [Github](https://github.com/SkyworkAI/Skywork-R1V)  |
| Apr 3, 2025  | [Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme](https://arxiv.org/abs/2504.02587)  | [Github](https://github.com/GAIR-NLP/MAYE)  |
| Apr 1, 2025  | [Improved Visual-Spatial Reasoning via R1-Zero-Like Training](https://arxiv.org/abs/2504.00883)  | [Github](https://github.com/zhijie-group/R1-Zero-VSI) |
| Apr 1, 2025  | [Think or Not Think: A Study of Explicit Thinking inRule-Based Visual Reinforcement Fine-Tuning](https://arxiv.org/abs/2503.16188)  | [Github](https://github.com/minglllli/CLS-RL)  |
| Mar 31, 2025  | [Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1](https://arxiv.org/abs/2503.24376)  | [Github](https://github.com/TencentARC/SEED-Bench-R1)  |
| Mar 28, 2025   | [OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning](https://arxiv.org/abs/2503.16081)  | - |
| Mar 27, 2025  | [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning](https://arxiv.org/abs/2503.20752)  | [Github](https://github.com/tanhuajie/Reason-RFT)  |
| Mar 27, 2025   | [Video-R1: Reinforcing Video Reasoning in MLLMs](https://arxiv.org/abs/2503.21776)                                                                   | [Github](https://github.com/tulerfeng/Video-R1)          |
| Mar 23, 2025   | [Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning](https://arxiv.org/abs/2503.18013) | [Github](https://github.com/jefferyZhan/Griffon/tree/master/Vision-R1) |
| Mar 21, 2025   | [OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement](https://arxiv.org/abs/2503.17352) | [Github](https://github.com/yihedeng9/OpenVLThinker) | 
| Mar 18, 2025   | [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://arxiv.org/abs/2503.15558)                                                | [Github](https://github.com/nvidia-cosmos/cosmos-reason1)  |
| Mar 18, 2025   | [DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding](https://arxiv.org/abs/2503.12797) | [Github](https://github.com/thunlp/DeepPerception)        |
| Mar 17, 2025   | [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://arxiv.org/abs/2503.12937) | [GitHub](https://github.com/jingyi0000/R1-VL)             |
| Mar 13, 2025   | [R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization](https://arxiv.org/abs/2503.10615)                       | [GitHub](https://github.com/Fancy-MLLM/R1-onevision)      |
| Mar 10, 2025   | [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://arxiv.org/abs/2503.07536)                       | [GitHub](https://github.com/TideDra/lmm-r1)               |
| Mar 10, 2025   | [MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning](https://arxiv.org/abs/2503.07365)                        | [GitHub](https://github.com/ModalMinds/MM-EUREKA)         |
| Mar 10, 2025   | [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://arxiv.org/abs/2503.07065)       | [GitHub](https://github.com/ding523/Curr_REFT)            |
| Mar 9, 2025    | [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://arxiv.org/abs/2503.06749)                                | [GitHub](https://github.com/Osilly/Vision-R1)             |
| Mar 7, 2025    | [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://arxiv.org/abs/2503.05132)                                                 | [GitHub](https://github.com/turningpoint-ai/VisualThinker-R1-Zero) |
| Mar 4, 2025    | [Visual-RFT: Visual Reinforcement Fine-Tuning](https://huggingface.co/papers/2503.01785)                                                             | [GitHub](https://github.com/Liuziyu77/Visual-RFT)         |
| Feb 27, 2025   | [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://arxiv.org/abs/2502.19634) | - |
| Feb 27, 2025   | [Med-RLVR: Emerging Medical Reasoning from a 3B base model via Reinforcement Learning](https://arxiv.org/abs/2502.19655)                             | - |
| Feb 20, 2025   | [AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO](https://arxiv.org/abs/2502.14669)                                        | [GitHub](https://github.com/menloresearch/visual-thinker) |

## Repositories Only
- [R1-V: Reinforcing Super Generalization Ability in Vision Language Models with Less Than $3](https://github.com/Deep-Agent/R1-V)
- [Multimodal Open R1](https://github.com/EvolvingLMMs-Lab/open-r1-multimodal)

## Surveys
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://arxiv.org/abs/2506.23918)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://arxiv.org/abs/2505.04921)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://arxiv.org/abs/2505.02567)
- [100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models](https://arxiv.org/abs/2505.00551)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://arxiv.org/abs/2504.03151)
- [A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://arxiv.org/abs/2503.21614) | [Github](https://github.com/XiaoYee/Awesome_Efficient_LRM_Reasoning)
- [Aligning Multimodal LLM with Human Preference: A Survey](https://arxiv.org/abs/2503.14504) | [Github](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Alignment)

multimodal_r1_papers

Download

Today's picks

Was this content helpful?

Recent Feedback

multimodal_r1_papers

Download

Today's picks

Was this content helpful?

Recent Feedback

Download README