Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Token Utility for On-Policy Distillation via Local Trust-Region Optimization
Narayanan Sadagopan, Yilan Chen, Vijay Lingam
Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-student disagreement, and mismat…
cs.LG2026
ExecTune: Effective Steering of Black-Box LLMs with Guide Models
Vijay Lingam, Aditya Golatkar, Anwesan Pal +6
For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize exp…