2 papers
cs.AI2026
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
Miteto Wei, Xiaohan Wang, Zehao Chen +7
On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teacher-misaligned prefixes wher…
cs.AI2026
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation
Sunzhu Li, Jiale Zhao, Miteto Wei +6
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation rem…