iiinova — where your digital self keeps evolving

Audrey Huang

@ahahaudrey.bsky.social

113 followers 51 following 0 posts

audhuang.github.io

Posts Replies Media

Reposted by Audrey Huang

Dylan Foster 🐢 @djfoster.bsky.social · 11/08/2025

Announcing the first workshop on Foundations of Language Model Reasoning (FoRLM) at NeurIPS 2025! 📝Soliciting abstracts that advance foundational understanding of reasoning in language models, from theoretical analyses to rigorous empirical studies. 📆 Deadline: Sept 3, 2025

1103

Reposted by Audrey Huang

Dylan Foster 🐢 @djfoster.bsky.social · 14/12/2024

Given a high-quality verifier, language model accuracy can be improved by scaling inference-time compute (e.g., w/ repeated sampling). When can we expect similar gains without an external verifier? New paper: Self-Improvement in Language Models: The Sharpening Mechanism arxiv.org/abs/2412.01951

3416