works on
bilingual document corpus 1document VQA 1layout and table analysis 1multimodal document parsing 1multi-task reinforcement learning 1synthetic data generation 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision

Chia-Hsuan Lee, Zelei Cheng, Yu Wang +4

On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts yield noisy gradie…