Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
DAPD: Dual-Anchored Policy Distillation
Jianyu Wu, Yizhou Wang, Encheng Su +2
On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged information but can induce a privilege ill…
cs.AI2026
SciIF: Benchmarking Scientific Instruction Following Towards Rigorous Scientific Intelligence
Encheng Su, Jianyu Wu, Chen Tang +9
As large language models (LLMs) transition from general knowledge retrieval to complex scientific discovery, their evaluation standards must also incorporate the rigorous norms of…