Mei-Lin Chen

Teach Me After You Learn It: Lookahead Self-Distillation for RLVR

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 distribution induced by privileged information. However, existing OPSD methods derive supervision solely from privileged information of the sam...

Targeted anthocyanin biofortification in black rice: a review of spatial metabolic control, growth–defence trade-offs and genotype–environment–management design