Pengcheng He

Deep Reinforcement Learning from Hierarchical Preference Design

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective

Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection

Deep Reinforcement Learning from Weak Hierarchical Preference Feedback