GitHub

View Ivan-Zhong's full-sized avatar

Block or report Ivan-Zhong

Pinned Loading

  1. A world-model-enhanced VLA for steerable dexterous manipulation, along with optimized training infra.

    Python 86 5

  2. An egocentric data pipeline that curates in-the-wild egocentric human videos into fully-annotated training data.

    Python 79 6

  3. A unified stack for teleoperation, model inference, and human-in-the-loop correction on a bimanual dexterous robot platform.

    Python 48 3

  4. Official implementation of HARL algorithms based on PyTorch.

    Python 942 134

  5. [AAAI'26 Oral] DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

    Python 559 45

  6. Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

    567 22

Read the original on github.com ↗