Awesome Robotics Manipulation · full_paper

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos

arXiv · 2026-01-07 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Latent Learning

视频规划VLALatent Learning基础模型机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos figure
AlphaXiv 中文论文页面（可滚动查看）