PPL
Yang Zhou
Papers (7)
MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM InferenceOISD: On-Policy Internal Self-Distillation of Language ModelsLearning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural RefinementLarge Dimensional Kernel Ridge Regression: Extending to Product KernelsEvidence Over Plans: Online Trajectory Verification for Skill DistillationDARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty EstimationForgeVLA: Federated Vision-Language-Action Learning without Language Annotations