MiroMindAI / MiroTrainLinks
MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.
☆77Updated this week
Alternatives and similar repositories for MiroTrain
Users that are interested in MiroTrain are comparing it to the libraries listed below
Sorting:
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆78Updated 3 months ago
- ☆52Updated 2 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning"☆142Updated 2 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆105Updated 3 months ago
- This repo contains the code for "MEGA-Bench Scaling Multimodal Evaluation to over 500 Real-World Tasks" [ICLR2025]☆74Updated 2 months ago
- The official code repository for the FullFront benchmark☆21Updated 3 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆311Updated 3 months ago
- 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…☆296Updated last week
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆55Updated 8 months ago
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆223Updated 3 weeks ago
- MMR1: Advancing the Frontiers of Multimodal Reasoning☆163Updated 5 months ago
- ☆69Updated 2 months ago
- Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay