Pinned Loading

1. Image-Generation-CoT Image-Generation-CoT Public

   [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation

   Python 844 26

2. CaraJ7/T2I-R1 CaraJ7/T2I-R1 Public

   [NeurIPS 2025] T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

   Python 423 24

3. Point-Bind_Point-LLM Point-Bind_Point-LLM Public

   Align 3D Point Cloud with Multi-modalities for Large Language Models

   Python 454 29

4. MME-CoF MME-CoF Public

   Are Video Models Ready as Zero-shot Reasoners?

   Python 84 4

5. Thinking-while-Generating Thinking-while-Generating Public

   The first Interleaved framework for textual reasoning within the visual generation process

   154 1

6. SAM2Point SAM2Point Public

   The Most Faithful Implementation of Segment Anything (SAM) in 3D

   Python 352 17