Christopher Manning @chrmanning · 24 Aug 2026
@RolandMemisevic @akarshkumar0101 @chrmanning I think that's a good bet too. Actually let me clarify that I don't really think of SMT as "distill transformers." It's joint optimization of a memory-bottlenecked transformer and an RNN. So it may be closer to your bet than it seems? See fig 10 for example.
30 582Views
37Likes
0Reposts
0Replies
1Quotes
0Bookmarks
Is that a lot?
1.03×vs this author's median29 579 views is typical
50Percentile for this authorof 8 recent posts
6.79×vs 100K–1M median4 505 views is typical
18.12%Reachviews ÷ followers
0.12%Engagement rateof viewers reacted