PPL
Wei Xu
Papers (5)
Learning to Route Languages for Multilingual Policy OptimizationDistribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM RegressionHand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm InterventionRankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action RankingHyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory