MLL Lab

Popular repositories Loading

1. RAGEN RAGEN Public

   Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics

   Python 2.8k 229

2. Awesome-Spatial-Intelligence-in-VLM Awesome-Spatial-Intelligence-in-VLM Public

   A paper list for spatial reasoning

   792 47

3. VAGEN VAGEN Public

   World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).

   Python 516 63

4. MindCube MindCube Public

   Benchmark and training code for MindCube: spatial mental modeling in vision-language models from limited views.

   Python 174 5

5. embodied-first-exam embodied-first-exam Public

   The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.

   Python 106 5

6. TStar TStar Public

   T* keyframe search for long-form video understanding (CVPR 2025) + LV-Haystack temporal search benchmark code

   Python 99 7