PPL
Fang Kong
Papers (5)
Harnesses for Inference-Time Alignment over Execution TrajectoriesA Regret Perspective on Online Multiple TestingEnhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword BridgingSample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution ShiftBest Arm Identification in Generalized Linear Bandits via Hybrid Feedback