PPL
Hui Xiong
Papers (7)
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language ModelsGraphs of Research: Citation Evolution Graphs as Supervision for Research Idea GenerationWhen Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMsSLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular EditingAttribution-Guided Continual Learning for Large Language ModelsQuantile Geometry Regularization for Distributional Reinforcement LearningSCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering