Hu, Yichun

5 publications

ICML 2025 Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation Zixuan Hu, Yichun Hu, Xiaotong Li, Shixiang Tang, Lingyu Duan

NeurIPS 2024 Contextual Linear Optimization with Bandit Feedback Yichun Hu, Nathan Kallus, Xiaojie Mao, Yanchen Wu

CVPR 2024 LEAD: Exploring Logit Space Evolution for Model Selection Zixuan Hu, Xiaotong Li, Shixiang Tang, Jun Liu, Yichun Hu, Ling-Yu Duan

COLT 2021 Fast Rates for the Regret of Offline Reinforcement Learning Yichun Hu, Nathan Kallus, Masatoshi Uehara

COLT 2020 Smooth Contextual Bandits: Bridging the Parametric and Non-Differentiable Regret Regimes Yichun Hu, Nathan Kallus, Xiaojie Mao