Yichun Hu
5 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (4) π Academic Marathon (5) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13)
π§
Keyword Pioneer
π
Cross-Pollinator
(14)
Conferences
COLT (2)
CVPR (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
regret bound
(3)
offline reinforcement learning
(1)
model selection
(1)
transfer learning
(1)
neural network optimization
(1)
fitted q-iteration
(1)
bandit feedback
(1)
bellman residual
(1)
offline learning
(1)
stochastic shortest path
(1)
contextual bandit
(1)
linear mdp
(1)
nonparametric method
(1)
smoothness parameter
(1)
logit space
(1)
tabular mdp
(1)
optimization dynamics
(1)
fine-tuning dynamics
(1)
contextual linear optimization
(1)
induced empirical risk minimization
(1)
Papers
Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
ICML 2025
Contextual Linear Optimization with Bandit Feedback
NIPS 2024
LEAD: Exploring Logit Space Evolution for Model Selection
CVPR 2024
Fast Rates for the Regret of Offline Reinforcement Learning
COLT 2021
Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes
COLT 2020