Sign in

aaditya6284.bsky.social

@aaditya6284.bsky.social
48 followers 51 following 11 posts
PostsRepliesMedia
Reposted by @aaditya6284.bsky.social
Stephanie Chan @scychan.bsky.social · 11/03/2025
New work led by @aaditya6284.bsky.social "Strategy coopetition explains the emergence and transience of in-context learning in transformers." We find some surprising things!! E.g. that circuits can simultaneously compete AND cooperate ("coopetition") 😯 🧵👇
294
aaditya6284.bsky.social @aaditya6284.bsky.social · 11/03/2025
Transformers employ different strategies through training to minimize loss, but how do these tradeoff and why? Excited to share our newest work, where we show remarkably rich competitive and cooperative interactions (termed "coopetition") as a transformer learns. Read on 🔎⏬
184
Reposted by @aaditya6284.bsky.social
Andrew Lampinen @lampinen.bsky.social · 10/12/2024
What counts as in-context learning (ICL)? Typically, you might think of it as learning a task from a few examples. However, we’ve just written a perspective (arxiv.org/abs/2412.03782) suggesting interpreting a much broader spectrum of behaviors as ICL! Quick summary thread: 1/7
arxiv.org
The broader spectrum of in-context learning
The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning...
212232