On-policy distillation (OPD) is increasingly applied to frontier foundation model post-training. Prior work in this area has largely focused on algorithmic advances, yet it remains unclear how much OPD depends on its training questions and, in particular, how far this dependence can be reduced. Across two representativ...
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· 0 citations
MAS-OPD is presented, where Role-Advantage Specialization defines the role advantage as the difference between the teacher signals under target and non-target role conditions, and Privileged Attribution for Coordination attributes an interaction conflict to its source and supplies it to the teacher alone as privileged...
Qi-Yong Zhong, Mao Zheng, Ming-Yang Song et al.· 0 citations
USA is proposed, which converts per-parameter update magnitudes measured during a brief warm-up into per-coordinate perturbation radii, reducing curvature precisely on the coordinates that carry most of the merging displacement.
Qi-Yong Zhong, Mao Zheng, Ming-Yang Song et al.· 1 citation
RAZOR, a training-free pruning method based on consensus residuals, the deviations of expert outputs from their original weighted mixture, gives the exact output change for a single deletion under survivor renormalization and router refill.
Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero is proposed.
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· arXiv.org· 24 citations· ⚡3
TrustMOPD replaces example-level teacher selection with label-free, token-level supervision allocation and closes the overall-score gap between the initial student and oracle-routed teachers when trained on single- and multi-teacher on-policy distillation.
Jie Sun, Mao Zheng, Ming-Yang Song et al.· 5 citations
DF-OPD matches and even surpasses real data, and the questions it produces track the teacher's own post-training data on three key diagnostics of training dynamics, which other real datasets do not.
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· 1 citation
Experiments on reasoning, code-generation, scientific-knowledge, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles.
Jie Sun, Mao Zheng, Mingyang Song et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
