Pinned Loading

1. aim-uofa/Omni-R1 aim-uofa/Omni-R1 Public

   [NeurIPS 2025] Official Repo of Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

   Python 124 5

2. aim-uofa/ReasonMatch aim-uofa/ReasonMatch Public

   [CVPR2026] Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching

   Python 15

3. Megatron-Bridge-slime Megatron-Bridge-slime Public

   Forked from coding-famer/Megatron-Bridge-slime

   Training library for Megatron-based models

   Python 1

4. sam2 sam2 Public

   Forked from facebookresearch/sam2

   my sam2 supporting hash caching of image features to boost inference

   Jupyter Notebook

5. sharegpt-tool sharegpt-tool Public

   A framework-agnostic toolkit for loading and converting custom style ShareGPT-format conversation datasets

   Python

6. vllm vllm Public

   Forked from vllm-project/vllm

   my fork of vLLM to support hybrid interleaved mrope on qwen3_omni_moe

   Python