PPL
Xinyu Liu
Papers (10)
OISD: On-Policy Internal Self-Distillation of Language ModelsBioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-SeriesMTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval BenchmarksTeacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy DivergenceOffline Two-Player Zero-Sum Markov Games with KL RegularizationOracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal ControlBeyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement LearningMathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical LibrariesConvergence and Emergence of In-Context Reinforcement Learning with Chain of ThoughtAlmost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift