3 papers
cs.LG2026
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation
Huanxin Sheng, Zhiling Ye, Haonan Wang +3
Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teacher guidance can yield a noisy…
cs.CV2026
Video-Based Reward Modeling for Computer-Use Agents
Linxin Song, Jieyu Zhang, Huanxin Sheng +6
Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this…
cs.CL2025
Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction
Huanxin Sheng, Xinyi Liu, Hangfeng He +2
LLM-as-a-judge has become a promising paradigm for using large language models (LLMs) to evaluate natural language generation (NLG), but the uncertainty of its evaluation remains u…