[ICLR 2026]🚀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.
☆213Dec 10, 2025Updated 6 months ago
Alternatives and similar repositories for Revisual-R1
Users that are interested in Revisual-R1 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆75Jul 13, 2025Updated 11 months ago
- instruction-following benchmark for large reasoning models☆48Apr 19, 2026Updated 2 months ago
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆66May 22, 2025Updated last year
- ✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints☆80Jul 10, 2025Updated 11 months ago
- ☆20Oct 12, 2025Updated 8 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆190Jun 5, 2025Updated last year
- OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.☆392Jun 1, 2025Updated last year
- SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward☆95Aug 8, 2025Updated 10 months ago
- ☆12Mar 22, 2025Updated last year
- [CVPR' 25] Official repo for From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Cal…☆22Jun 6, 2025Updated last year
- ☆138Feb 4, 2026Updated 4 months ago
- ☆71Jul 8, 2025Updated 11 months ago
- Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training☆54Dec 13, 2025Updated 6 months ago
- [ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos☆28Jun 4, 2026Updated 3 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Open-Pandora: On-the-fly Control Video Generation☆35Nov 28, 2024Updated last year
- ☆24Jun 18, 2025Updated last year
- [ICML 2025] Official Implementation of GLIDER☆74Oct 9, 2025Updated 8 months ago
- RewardAnything: Generalizable Principle-Following Reward Models☆44Jun 11, 2025Updated last year
- Codes for ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding [ICML 2025]]☆50Jul 22, 2025Updated 11 months ago
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆38Feb 25, 2026Updated 4 months ago
- [ICCV 2025] Boosting MLLM Reasoning with Text-Debiased Hint-GRPO☆48Jul 1, 2025Updated 11 months ago
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆103May 20, 2025Updated last year
- [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations [ICML…☆185Mar 29, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code repository for the ICML 2026 paper "Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation".☆24Jun 14, 2026Updated 2 weeks ago
- [ICLR 2026] The official repository for the paper "AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning".☆81Feb 27, 2026Updated 4 months ago
- Resources for the Enigmata Project.☆82Aug 13, 2025Updated 10 months ago
- We propose VidSketch, the first method capable of generating high-quality video animations directly from any number of hand-drawn sketche…☆22Jun 10, 2025Updated last year
- 🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts☆41Sep 29, 2024Updated last year
- IITM Paradigms of Programming -- Monsoon 2025☆18Nov 17, 2025Updated 7 months ago
- ☆139Jun 6, 2025Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆453Mar 20, 2026Updated 3 months ago
- MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning☆771Sep 7, 2025Updated 9 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆24Jul 8, 2023Updated 2 years ago
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆110Sep 18, 2025Updated 9 months ago
- The official codebase for "Experiential Reinforcement Learning" - https://arxiv.org/pdf/2602.13949v1☆72May 8, 2026Updated last month
- Analyzing LLM Alignment via Token distribution shift☆18Jan 26, 2024Updated 2 years ago
- ViLoMem: Agentic Learner with Grow-and-Refine Multimodal Semantic Memory☆66Apr 21, 2026Updated 2 months ago
- 记录Transformer升级的论文笔记☆19Jun 25, 2023Updated 3 years ago
- Collect the awesome works evolved around reasoning models like O1/R1 in visual domain☆55Jul 21, 2025Updated 11 months ago