tweetindex

Deepak Pathak @deepakpathak · 26 Aug 2026

This is a good question. If the task was only 5–10s long, it can be difficult to distinguish true physical steerability from generalization. But we’re doing tasks that run for over 10 minutes and not seen during training (OOD). Sustaining performance at such long horizon and
12 723Views
80Likes
4Reposts
3Replies
0Quotes
36Bookmarks

Is that a lot?

0.77×vs this author's median16 472 views is typical
12Percentile for this authorof 8 recent posts
4.62×vs 10K–100K median2 751 views is typical
42.51%Reachviews ÷ followers
0.68%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →