Pinned Loading

1. open-compass/VLMEvalKit open-compass/VLMEvalKit Public

   Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

   Python 4k 677

2. InternLM/ARM-Thinker InternLM/ARM-Thinker Public

   [CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"

   Python 186 13

3. MM-IFEngine MM-IFEngine Public

   [ICCV 2025] MM-IFEngine: Towards Multimodal Instruction Following

   Python 121 1

4. Skill-Anything Skill-Anything Public

   Any source (PDF, video, web, audio, text) to interactive learning package with quizzes, flashcards and spaced repetition. One command, 12-section study guide.

   Python 192 8

5. InternLM/Visual-ERM InternLM/Visual-ERM Public

   Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"

   Python 61

6. PhoenixZ810/OmniAlign-V PhoenixZ810/OmniAlign-V Public

   Official Repository of ACL 2025 paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

   Python 144 2