Zhiqing Sun

Lean-STaR: Learning to Interleave Thinking and Proving

Self-Play Preference Optimization for Language Model Alignment

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving

Aligning Multimodal Models for Clinical Reasoning using Rule-based Rewards

Improve Vision Language Model Chain-of-thought Reasoning

Sampling-Enhanced Large Neighborhood Search for Solving Integer Linear Programs

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

SALMON: Self-Alignment with Instructable Reward Models

Aligning Large Multimodal Models with Factually Augmented RLHF

An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

DIFUSCO-LNS: Diffusion-Guided Large Neighbourhood Search for Integer Linear Programming