Pinned Loading

1. TokenExpansion TokenExpansion Public

   [CVPR 2024] The official pytorch implementation of "A General and Efficient Training for Transformer via Token Expansion".

   Python 47 3

2. dynamic_llava dynamic_llava Public

   [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification".

   Python 74 2

3. Vision-R1 Vision-R1 Public

   [ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incen…

   Python 1.6k 27

4. Awesome-Interleaving-Reasoning Awesome-Interleaving-Reasoning Public

   Interleaving Reasoning: Next-Generation Reasoning Systems for AGI

   283 14

5. Interleaving-Reasoning-Generation Interleaving-Reasoning-Generation Public

   [ICLR 2026] This is an early exploration to introduce Interleaving Reasoning to Text-to-image Generation field and achieve the SoTA benchmark performance. It also significantly improves the quality…

   Python 100 1

6. Vision-DeepResearch Vision-DeepResearch Public

   [ICML 2026 & EMNLP 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of searc…

   Python 690 56