3 papers
cs.LG2026
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
Nan Jia, Haojin Yang, Xing Ma +6
On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy distillation and standard reinforcement lea…
cs.SE2025
An Empirical Framework for Evaluating Semantic Preservation Using Hugging Face
Nan Jia, Anita Raja, Raffi Khatchadourian
As machine learning (ML) becomes an integral part of high-autonomy systems, it is critical to ensure the trustworthiness of learning-enabled software systems (LESS). Yet, the nonde…
cs.SE2025
Speculative Automated Refactoring of Imperative Deep Learning Programs to Graph Execution
Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh +2
Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- s…