Authors

Yuhang Zang

Publications 2

Preprint Open access

ResOPD: Tail Residualization for Sparse On-Policy Distillation

Penghui Yang, Long Xing, Xuanlang Dai et al. · 2026

On-policy distillation (OPD) trains a student model on self-generated trajectories, but transmitting dense teacher distributions across long reasoning traces creates prohibitive communication and memory bottlenecks. Practical systems therefore rely on sparse teacher interfaces, typically transmitting either the sampled …

Preprint Open access

CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models

Pengyang Ling, Jiazi Bu, Yu-Jie Zhou et al. · 2026

Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consolidates their capabilities into a single student. Existing methods, however, route each prompt to a single teacher according to its semantic category, implicitly binding the d …

Co-authors