5 papers
SPL-LNS: Sampling-Enhanced Large Neighborhood Search for Solving Integer Linear Programs
Shengyu Feng, Zhiqing Sun, Yiming Yang
Large Neighborhood Search (LNS) is a common heuristic in combinatorial optimization that iteratively searches over a large neighborhood of the current solution for a better one. Re…
Lean-STaR: Learning to Interleave Thinking and Proving
Haohan Lin, Zhiqing Sun, Sean Welleck +1
Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is…
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Yangzhen Wu, Zhiqing Sun, Shanda Li +2
While the scaling laws of large language models (LLMs) training have been extensively studied, optimal inference configurations of LLMs remain underexplored. We study inference sca…
Improve Vision Language Model Chain-of-thought Reasoning
Ruohong Zhang, Bowen Zhang, Yanghao Li +6
Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT r…
Self-Play Preference Optimization for Language Model Alignment
Yue Wu, Zhiqing Sun, Huizhuo Yuan +3
Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrat…