Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Teach Me After You Learn It: Lookahead Self-Distillation for RLVR
Zepeng Zhai, Meilin Chen
On-policy self-distillation (OPSD) has emerged as a popular training paradigm for LLMs, providing dense, token-level supervision by aligning a model's own distribution with the dis…
cs.LG2026
Rewards as Labels: Revisiting RLVR from a Classification Perspective
Zepeng Zhai, Meilin Chen, Jiaxuan Zhao +3
Reinforcement Learning with Verifiable Rewards has recently advanced the capabilities of Large Language Models in complex reasoning tasks by providing explicit rule-based supervisi…