On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth question-answer pairs, human-curate
1 comments
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models was first seen on Hugging Face · Daily papers on Oct 26, 2026. Since then it appeared in 9 hourly checks across 2 days, peaking at #8 on Oct 27, 03:28 UTC. It was last on the list on Oct 27, 03:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Show that this trended, linking back to this page.
<a href="https://trendoday.com/hugging-face/papers/2610.32770-on-policy-self-training-data-free-self-improvement-in-large"><img src="https://trendoday.com/badge/hugging-face/papers/2610.32770-on-policy-self-training-data-free-self-improvement-in-large.svg" alt="On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models on TrendBoard" height="44"></a>
[](https://trendoday.com/hugging-face/papers/2610.32770-on-policy-self-training-data-free-self-improvement-in-large)