Stanford: Physically Grounded Vision-Language Models for Robotic Manipulation (arxiv.org)

1 points by socratic1 2y ago ↗ HN

0 comments

[ 3.8 ms ] story [ 105 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats