Runxue Bao

I am currently an AI Research Scientist with the Foundation AI team at GE Healthcare. Prior to this, I earned my Ph.D. in Computer Engineering from the University of Pittsburgh and completed my Honours B.S. in Electrical Engineering at the University of Science and Technology of China.

My current work focuses on research and applications of Large Language Models (LLMs), with a particular emphasis on:

• Parameter-Efficient Fine-Tuning (PEFT), Retrieval-Augmented Generation (RAG), and In-Context Learning (ICL)
• Transfer Learning in Healthcare
• Model Compression and Optimization

I’m open to collaboration opportunities—feel free to connect!

News

• [09/24] Two papers on LLMs were accepted by EMNLP 2024! One focuses on Estimating LLM Memorization and the other explores Enhancing LLMs with Knowledge Graphs!
• [06/24] One paper on Online Transfer Learning received ICHI 2024 Best Paper Award (Analytics Track)!
• [05/24] One paper on Graph Neural Network was accepted by MICCAI 2024!
• [03/24] One paper on LLM Pruning was accepted by NAACL 2024!
• [03/24] One paper on Online Transfer Learning was accepted by IEEE ICHI 2024!
• [02/24] One paper on Model Compression was accepted by CVPR 2024!
• [01/24] Two papers on Transfer Learning and Multimodal Learning were accepted by ISBI 2024!
• [10/23] One survey paper on Heterogeneous Transfer Learning was on arXiv!
• [08/23] One paper on Online Pairwise Learning was accepted by IEEE TNNLS 2023!

Selected Publications

• Unlocking Memorization in Large Language Models with Dynamic Soft Prompting [Paper]
  Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang.
  EMNLP 2024
• InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration [Paper]
  Fali Wang, Runxue Bao, Suhang Wang, Wenchao Yu, Yanchi Liu, Wei Cheng, Haifeng Chen.
  EMNLP 2024
• Self-guided Knowledge-injected Graph Neural Network for Alzheimer’s Diseases [Paper]
  Zhepeng Wang, Runxue Bao, Yawen Wu, Guodong Liu, Lei Yang, Liang Zhan, Feng Zheng, Weiwen Jiang, Yanfu Zhang.
  MICCAI 2024
• Pruning as a Domain-specific LLM Extractor [Paper]
  Nan Zhang, Yanchi Liu, Xujiang Zhao, Wei Cheng, Runxue Bao, Rui Zhang, Prasenjit Mitra, Haifeng Chen.
  NAACL 2024
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [Paper]
  Xidong Wu, Shangqian Gao, Zeyu Zhang, Zhenzhen Li, Runxue Bao, Yanfu Zhang, Xiaoqian Wang, Heng Huang.
  CVPR 2024
• Neurodegenerative Disease Prediction via Transferable Deep Networks [Paper]
  Yanfu Zhang, Guodong Liu, Runxue Bao, Liang Zhan, Paul Thompson, Heng Huang.
  ISBI 2024
• Brain Image Synthesis Using Incomplete Multimodal Data [Paper]
  Yanfu Zhang, Guodong Liu, Runxue Bao, Liang Zhan, Paul Thompson, Heng Huang.
  ISBI 2024
• Online Transfer Learning for RSV Case Detection [Paper]
  Yiming Sun, Yuhe Gao, Runxue Bao, Gregory F Cooper, Jessi Espino, Harry Hochheiser, Marian G Michaels, John M Aronis, Ye Ye.
  ICHI 2024 (Best Paper Award)
• A Survey of Heterogeneous Transfer Learning [Paper]
  Runxue Bao*, Yiming Sun*, Yuhe Gao, Jindong Wang, Qiang Yang, Haifeng Chen, Zhi-Hong Mao, Ye Ye.
  arXiv 2023
• New Scalable and Efficient Online Pairwise Learning Algorithm [Paper]
  Bin Gu, Runxue Bao, Chenkang Zhang, Heng Huang.
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS 2023)
• Prediction of COVID-19 Patients’ Emergency Room Revisit using Multi-Source Transfer Learning [Paper]
  Yuelyu Ji*, Yuhe Gao*, Runxue Bao*, Qi Li, Disheng Liu, Yiming Sun, and Ye Ye. (* denotes equal contribution)
  ICHI 2023
• An Accelerated Doubly Stochastic Gradient Method with Faster Explicit Model Identification [Paper] [Slides]
  Runxue Bao, Bin Gu, Heng Huang.
  CIKM 2022
• Doubly Sparse Asynchronous Learning for Stochastic Composite Optimization [Paper] [Slides]
  Runxue Bao, Xidong Wu, Wenhan Xian, Heng Huang.
  IJCAI 2022
• Toward Unified Data and Algorithm Fairness via Adversarial Data Augmentation and Adaptive Model Fine-tuning [Paper]
  Yanfu Zhang, Runxue Bao, Jian Pei, Heng Huang.
  ICDM 2022
• Fast OSCAR and OWL Regression via Safe Screening Rules [Paper] [Code] [Slides]
  Runxue Bao, Bin Gu, Heng Huang.
  ICML 2020
• Efficient Approximate Solution Path Algorithm for Ordered Weighted L_1-Norm with Accuracy Guarantee [Paper]
  Runxue Bao, Bin Gu, Heng Huang.
  ICDM 2019

Services

• Conference Program Committee or Reviewer:
  • 2025: ICLR, AAAI, AISTATS, WACV
  • 2024: ICML, ICLR, NeurIPS, NeurIPS Datasets and Benchmarks Track, CVPR, ECCV, AAAI, IJCAI, WACV, WSDM (PC), SDM, IEEE CAI, AutoML, LOG
  • 2023: ICLR, ICML, NeurIPS, NeurIPS Datasets and Benchmarks Track, KDD (PC), IJCAI (PC), ECAI, WACV, AMIA, IEEE CEC, FUZZ-IEEE, AutoML, LOG
  • 2022: ICML, NeurIPS, NeurIPS Datasets and Benchmarks Track, ICLR, AISTATS, IEEE WCCI, LOG
  • 2021: ICML, NeurIPS
  • 2020: KDD (PC), MLSP
  • 2019: MLSP
• Journal Reviewer:
  • Briefings in Bioinformatics
  • Artificial Intelligence in Medicine
  • IEEE Transactions on Big Data
  • Patterns
  • Knowledge and Information Systems (KAIS)
  • Journal of Combinatorial Optimization
  • IEEE Open Journal of the Computer Society (OJCS)