PPL
Yang Li
Papers (13)
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary EnhancementWhen Search Becomes Memory: Turning Robot Design Trials into Transferable SkillsSparse Compositional Flow Matching by geometric assembly from motion primitivesWeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization ProblemsBeyond Mode Collapse: Distribution Matching for Diverse ReasoningWhat and When to Distill: Selective Hindsight Distillation for Multi-Turn AgentsHeterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model TrainingTabQL: In-Context Q-Learning with Tabular Foundation ModelsOne Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative PerceptionLearning from Language Feedback via Variational Policy DistillationKAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural InterpretationForge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMsA$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping