On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can we assess whether a newly ge
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can we assess whether a newly ge
Details from Hugging Face ↗.
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation was first seen on Hugging Face · Daily papers on Oct 22, 2026. Since then it has appeared in 6 checks on 1 different day. Its best position was #16 of 30, reached on Oct 22, 03:18 UTC. It dropped off the list after Oct 22, 11:18 UTC.
This page has little history so far; it stays out of search results until the item has trended on two days or has more context.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Oct 22, 11:18 UTC, after 1 day of trending.
#16 on Hugging Face · Daily papers, on Oct 22, 03:18 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 22, 2026 and has been on the list on 1 day (6 checks) since.