PPL
Hang Yu
Papers (6)
Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation LearningTraining Neural Networks with Optimal Double-Bayesian LearningML-Embed: Inclusive and Efficient Embeddings for a Multilingual WorldVerifier-Free RL for LLMs via Intrinsic Gradient-Norm RewardACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-NetworkBeyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning