Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
ReTaCo: Residual-Target Control for On-Policy Distillation
Zixiang Ni, Zhuo Hu, Renjie Cao +8
On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher's full-vocabulary distributio…
cs.LG2026
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Hao Li, MeiJia Chen, Weijie Ren +4
On-policy distillation (OPD) trains a student to match the teacher's next-token distributions on the student's own trajectories and has yielded substantial empirical gains. General…