Pinned Loading

1. robust-world-model-planning robust-world-model-planning Public

   Code for "Closing the Train-Test Gap in World Models for Gradient-Based Planning"

   Python 67 2

2. haizelabs/verdict haizelabs/verdict Public

   Inference-time scaling for LLMs-as-a-judge.

   Jupyter Notebook 316 24

3. haizelabs/j1-micro haizelabs/j1-micro Public

   j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.

   Python 99 6

4. bradyz/task-distillation bradyz/task-distillation Public

   Code for Domain Adaptation Through Task Distillation (ECCV 20)

   Python 48 4

5. robomaster-driver robomaster-driver Public

   DJI RoboMaster S1 Driver for Evaluating Real-World Deep Visuomotor Policies

   Python

6. gg gg Public

   [deprecated] git workflow shortcuts

   Shell 1.4k 51