← Wednesday, September 30, 2026Models & trainingPaper

SAKI routes teacher supervision through coupled on-policy rollouts

huggingface.co by Miteto Wei et al. Editor score 8/10

SAKI uses maximal coupling to direct token-level supervision and an engine-resident verifier that raises matched-workload rollout throughput 4.22×; it also improves Mean@8 and Pass@8 for two student sizes across seven math benchmarks. The method links post-training supervision choices to a concrete rollout-throughput gain.

What: SAKI routes token-level teacher supervision using accept/correction events from a KL-constrained teacher-guided rollout with maximal coupling.
Method: Accepted positions retain sampled-token reverse-KL supervision; correction positions receive direct supervision on the teacher’s highest-probability token.
Why it matters: Its engine-resident speculative verifier preserves exact-q trajectory distribution and coupling semantics while improving matched-workload rollout throughput by 4.22x.

Maximal coupling events route rollout positions to different forms of token supervision. Sketched from the article's own text.

Read on huggingface.co → Code · 1 stars

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.