LAMDA Nanjing University

Guanlin Li

Ph.D. Student

School of Artificial Intelligence
Nanjing University

Advisor: Prof. Chao Qian

ligl@lamda.nju.edu.cn

Guanlin Li

About Me

I am a first-year Ph.D. student at the School of Artificial Intelligence, Nanjing University, and a member of the LAMDA Group, advised by Prof. Chao Qian.

My research focuses on combinatorial optimization, with a particular interest in solving mixed-integer programming problems. My recent work explores learning-based methods for accelerating mixed-integer linear programming (MILP) solvers.

During my undergraduate studies, I also worked on ReLAM, a reward learning framework for visual robotic manipulation, published at ICML 2026.

Education

– Present

Nanjing University

Ph.D. studies

School of Artificial Intelligence

Advisor: Prof. Chao Qian

–

Nanjing University

Undergraduate studies in Information and Computing Science

School of Computer Science

Publications

ICML 2026

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation

Nan Tang, Jing-Cheng Pang, Guanlin Li, Chao Qian, Yang Yu

43rd International Conference on Machine Learning, 2026.

Work conducted during my undergraduate studies.

Learning anticipation models from action-free videos to provide structured, dense rewards for visual robotic manipulation.

OpenReview arXiv PDF Download BibTeX
Show BibTeX 
@inproceedings{tang2026relam,
  title={Re{LAM}: Learning Anticipation Model for Rewarding Visual Robotic Manipulation},
  author={Nan Tang and Jing-Cheng Pang and Guanlin Li and Chao Qian and Yang Yu},
  booktitle={Forty-third International Conference on Machine Learning},
  year={2026},
  url={https://openreview.net/forum?id=4XHiXa48fA}
}

Preprints

arXiv 2026

SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming

Zherong Zhang, Guanlin Li, Chengrui Gao, Haopu Shang, Ke Xue, Jixiang Lu, Weiyong Yang, Chao Qian

arXiv preprint, arXiv:2608.25282, 2026.

Using constraint structure to predict MILP solutions hierarchically, with confidence-aware repair of intermediate predictions.

arXiv PDF Download BibTeX
Show BibTeX 
@misc{zhang2026shsp,
  title={{SHSP}: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming},
  author={Zherong Zhang and Guanlin Li and Chengrui Gao and Haopu Shang and Ke Xue and Jixiang Lu and Weiyong Yang and Chao Qian},
  year={2026},
  eprint={2608.25282},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2608.25282}
}
arXiv 2026

Learning Early-to-Final Solution Consistency for MILP Acceleration

Guanlin Li, Chengrui Gao, Chenguang Wang, Haopu Shang, Zherong Zhang, Ke Xue, Jixiang Lu, Weiyong Yang, Chao Qian

arXiv preprint, arXiv:2608.19953, 2026.

Learning which variable assignments in early-stage solutions remain consistent with full-budget solutions to guide MILP search.

arXiv PDF Download BibTeX
Show BibTeX 
@misc{li2026consistency,
  title={Learning Early-to-Final Solution Consistency for {MILP} Acceleration},
  author={Guanlin Li and Chengrui Gao and Chenguang Wang and Haopu Shang and Zherong Zhang and Ke Xue and Jixiang Lu and Weiyong Yang and Chao Qian},
  year={2026},
  eprint={2608.19953},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2608.19953}
}