Pinned Loading

1. RoboGaze RoboGaze Public

   Repository associated with paper titled "RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis"

   Python 124 3

2. CLP_VLA CLP_VLA Public

   Repository associated with paper titled "CLP: Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think"

   Jupyter Notebook 84 2

3. FOCA FOCA Public

   Repository associated with paper titled "FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation", presented at ICML 2026.

   Python 78 3

4. vla.simd vla.simd Public

   A pure C++ inference engine for VLA policies on CPUs, with no GPU, CUDA, or ggml dependency. Built with its own tensors, operators, and SIMD kernels, the engine keeps kernels easy to inspect, tune,…

   C++ 36 1

5. roboworm roboworm Public

   RoboWorM: Evaluating Movement Realism, Consistency and Acceleration Affects in Embodied Video World Models

   Python 23 1

6. FoldQuantVLA FoldQuantVLA Public

   FoldQuant: offline folding for W4A4 / W8A8 vision-language-action inference on edge GPUs

   Python 40 8