aim-uofa / Active-o3Links
ACTIVE-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
☆74Updated 5 months ago
Alternatives and similar repositories for Active-o3
Users that are interested in Active-o3 are comparing it to the libraries listed below
Sorting:
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆94Updated 2 months ago
- Official implementation of "Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence"☆48Updated last week
- Visual Planning: Let's Think Only with Images☆280Updated 5 months ago
- [NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration☆85Updated 4 months ago
- ☆91Updated 4 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆170Updated 2 weeks ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆165Updated last month
- ☆41Updated 4 months ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆92Updated 3 months ago
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆76Updated 3 months ago
- ☆52Updated 5 months ago
- [NeurIPS 2025] The official repository for our paper, "Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reason…☆143Updated last month
- ☆61Updated 3 months ago
- High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning☆50Updated 3 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆184Updated 3 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆75Updated 3 months ago
- Official implementation of "Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology"☆68Updated 3 months ago
- Pixel-Level Reasoning Model trained with RL [NeuIPS25]☆243Updated last month
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆91Updated 8 months ago
- ☆99Updated 3 months ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆191Updated 5 months ago
- ☆28Updated 3 months ago
- STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?☆30Updated 3 months ago
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆34Updated this week
- ☆260Updated 2 weeks ago
- Code and dataset link for "DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"☆112Updated 3 weeks ago
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆39Updated 8 months ago
- ☆76Updated 4 months ago
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces☆84Updated 4 months ago
- ☆30Updated 10 months ago