CSfufu / Revisual-R1Links
🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal reinforcement learning, and text-only reinforcement learning—to achieve faithful, concise, and self-reflective state-of-the-art performance in visual and textual reasoning.
☆178Updated 2 months ago
Alternatives and similar repositories for Revisual-R1
Users that are interested in Revisual-R1 are comparing it to the libraries listed below
Sorting:
- OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.☆303Updated 3 months ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆141Updated 5 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆144Updated 3 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆107Updated 3 months ago
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆109Updated last month
- MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search too…☆312Updated 3 weeks ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆312Updated 3 months ago
- ☆95Updated 3 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆152Updated last week
- MMR1: Advancing the Frontiers of Multimodal Reasoning☆163Updated 6 months ago
- [ICCV 2025 Highlight] The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"☆169Updated 6 months ago
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆144Updated 5 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆190Updated 6 months ago
- [CVPR2025 Highlight] Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models☆221Updated 2 months ago
- Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"☆268Updated this week
- The official repository for our paper, "Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning".☆138Updated last week
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆162Updated 4 months ago
- Towards a Unified View of Large Language Model Post-Training☆134Updated last week
- Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay☆122Updated 3 months ago
- ☆88Updated 8 months ago
- repo for paper https://arxiv.org/abs/2504.13837☆190Updated 2 months ago
- Extrapolating RLVR to General Domains without Verifiers☆160Updated last month
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆150Updated this week
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models☆132Updated 4 months ago
- ☆129Updated 2 weeks ago
- Pixel-Level Reasoning Model trained with RL☆204Updated last week
- "what, how, where, and how well? a survey on test-time scaling in large language models" repository☆67Updated this week
- ☆331Updated last month
- Geometric-Mean Policy Optimization☆79Updated last month
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆230Updated last month