2 papers
cs.LG2026
Let the Data Decide: Supervision Analysis, Capability Trade-offs, and Adaptive Objective Routing in Continued Pre-Training via Off-Policy Distillation
Jiangan Yuan, Zhixuan Li, Han Xu
Off-policy distillation is now central to large language model pre-training, yet how training data, objective parameterization, and model capabilities interact remains poorly chara…
cs.AI2026
Data and Evaluation Closed-Loop for Model Capability Enhancement
Zhixuan Li, Jiangan Yuan, Han Xu
Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compre…