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"