Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy Distillation
On-policy distillation (OPD) has recently been introduced as a promising paradigm for continual learning, where a student policy can be supervised at the token-level. Typically, OPD is performed using a single teacher per prompt rollout (or even per training run). However, this ignores a whole other axis of flexibility...
Stanley Wei, Jiin Woo, Kaan Ozkara et al.
· 0 citations