2 papers
cs.LG2026
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Yuying Li, Leqi Zheng, Yongzi Yu +6
On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on…
cs.AI2026
Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection
Yongzi Yu, Ao Li, Le Wang +4
Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in high-stakes industrial scen…