Zhichen Dong

Emergent Response Planning in LLMs

L2P-MIP: Learning to Presolve for Mixed Integer Programming

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models

Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach

BTBS-LNS: A Binarized-Tightening, Branch and Search Approach of Learning Large Neighborhood Search Policies for MIP