Labs & Research4 min read
On-policy distillation | Folding EOPD and ToDi into one family
A 33-of-36 result, published with the authors' own asterisk
A four-coefficient family for gating per-token losses in on-policy distillation beats single-channel baselines in 33 of 36 cells. The authors then call their own counts directional evidence and their three-seed replications not significant.
2026-09-20