Hongyu Cao

Clemson University

Clemson, South Carolina, USA

hcao2@clemson.edu

I am a PhD student in Computer Science at Clemson University (2026 – present). I received my Master’s degree in Computer Science from the University of Science and Technology of China (USTC) in May 2025, and my Bachelor’s degree in Computer Science from USTC in May 2022.

My research interests lie in Deep Learning and Machine Learning, with a particular focus on Large Language Models (LLMs). I have experience in LoRA finetuning, Retrieval-Augmented Generation (RAG), contrastive learning, and prompt learning. My applied work spans supply chain decision-making with LLMs and sentiment-controlled text summarization.

I have been awarded the USTC Scholarship three times (Autumn 2022, Spring 2023, Autumn 2023).

news

Jan 01, 2026	Transferred to Clemson University to continue my PhD in Computer Science!
May 01, 2025	Paper “Enhancing LLMs Decision-making for Supply Chain with Cluster and RAG” accepted at BigData 2025!
Apr 01, 2024	Paper “Desentiment: A New Method to Control Sentimental Tendency During Summary Generation” accepted at MDPI Information!

latest posts

Dec 04, 2024	a post with image galleries
May 14, 2024	Google Gemini updates: Flash 1.5, Gemma 2 and Project Astra
May 01, 2024	a post with tabs

selected publications

Preprint

Parking Without Building: Agentic AI for Parking Planning Through Urban Contradiction Reasoning

Hongyu Cao, David A. King, Xinyuan Wang, and 4 more authors

Preprint, 2026

Abs Bib

@article{cao2026parking,
  title = {Parking Without Building: Agentic AI for Parking Planning Through Urban Contradiction Reasoning},
  author = {Cao, Hongyu and King, David A. and Wang, Xinyuan and Malarkkan, Arun Vignesh and Liu, Kunpeng and Wang, Dongjie and Fu, Yanjie},
  journal = {Preprint},
  year = {2026},
}

arXiv
Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach

Hongyu Cao, Kunpeng Liu, Dongjie Wang, and 1 more author

arXiv preprint arXiv:2603.20899, 2026

Abs arXiv Bib

Shortcut-Aware Reasoning Training (SART), a gradient-aware framework that detects and mitigates shortcut-promoting samples via a shortcut score and gradient surgery, improving reasoning generalization under distribution shifts.
@article{cao2026mitigating, title = {Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach}, author = {Cao, Hongyu and Liu, Kunpeng and Wang, Dongjie and Fu, Yanjie}, journal = {arXiv preprint arXiv:2603.20899}, year = {2026}, }
arXiv
Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation

Hongyu Cao, Jinghan Zhang, Kunpeng Liu, and 5 more authors

arXiv preprint arXiv:2603.09053, 2026

Abs arXiv Bib

A robust simulation-to-decision framework that re-weights simulation errors in decision-critical state-action pairs through adversarial calibration and stabilizes policy preferences with a group-relative perturbation strategy.
@article{cao2026sim2act, title = {Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation}, author = {Cao, Hongyu and Zhang, Jinghan and Liu, Kunpeng and Wang, Dongjie and Xia, Feng and Chen, Haifeng and Hu, Xia and Fu, Yanjie}, journal = {arXiv preprint arXiv:2603.09053}, year = {2026}, }
BigData
Structured Memory and Role-Aware Decision Making for Supply Chain Transportation

Hongyu Cao, Haoyue Bai, and Yanjie Fu

In 2025 IEEE International Conference on Big Data (BigData), 2025

Abs Bib

A decision-making method for supply chain transportation that combines structured memory with role-aware reasoning to improve large language model decisions.
@inproceedings{cao2025structured, title = {Structured Memory and Role-Aware Decision Making for Supply Chain Transportation}, author = {Cao, Hongyu and Bai, Haoyue and Fu, Yanjie}, booktitle = {2025 IEEE International Conference on Big Data (BigData)}, pages = {1837--1846}, year = {2025}, }