8 citations · 14 across the 29 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Rethinking Relative Policy Differences Transfer of On-Policy Distillation
Rong Wu, Daocheng Fu, Yu Yang +9
On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantial…
cs.LG2026
Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update
Daocheng Fu, Rong Wu, Yu Yang +7
Post-training for large language models typically couples policy exploration with model optimization, hindering the reuse of high-reward behaviors from policy exploration. While on…