Sean McLeish @SeanMcleish · 11 Nov 2025
First, we find that initializing from pretrained models is better than random initialization, so we can transfer knowledge from static depth models into looped models. 2/7 https://t.co/qegGDIZ88s
2 273Views
39Likes
0Reposts
1Replies
0Quotes
3Bookmarks
Is that a lot?
0.60×vs under 10K median3 808 views is typical
3.4× audienceReachviews ÷ followers
1.76%Engagement rateof viewers reacted