Ziyi Yang

Scaling Laws of Synthetic Data for Language Model

Segmenting Text and Learning Their Rewards for Improved RLHF in Language Models

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses

Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization