PPL
Anh Tuan Luu
Papers (4)
WINDQuant: Weight-Informed Neural Decision-Making for Global Mixed-Precision LLM QuantizationWhen In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference ShiftUnderstanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow OptimizationTracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models