Christopher Manning @chrmanning · 23 Aug 2026
Pretraining Recurrent Networks without Recurrence by @akarshkumar0101 & @phillip_isola is a great paper! It makes an end-run around the problems of RNNs via a transformer teacher to learn good predictive state representations & supervised learning of a memory transition function https://t.co/lKGK3wfbe2
100 126Views
917Likes
112Reposts
16Replies
8Quotes
848Bookmarks
Is that a lot?
3.39×vs this author's median29 579 views is typical
88Percentile for this authorof 8 recent posts
22.2×vs 100K–1M median4 505 views is typical
59.34%Reachviews ÷ followers
1.05%Engagement rateof viewers reacted