CV

Research Assistant

University of Virginia

Conduct machine learning research with topics covering computer vision, natural language processing, and bioinformatics.

• Lead research on enhancing robustness in machine learning models, with a particular focus on visual and language domains
• Publish papers in leading AI and data mining conferences; develop and maintain open-source solutions
• Collaborate with bioengineering researchers to develop innovative machine learning models utilizing genomic interval data

Large Language Model Optimization for Genomics

Technologies Used: PyTorch, Transformer models, Retrieval-Augmented Generation (RAG), Model and Data Parallelism, GPU Clusters (NVIDIA A100)

• Developed and fine-tuned state-of-the-art LLMs for answering questions in genomics
• Implemented advanced techniques like Retrieval-Augmented Generation to enhance contextual understanding of the models
• Employed data and model parallelism techniques for efficient training of large-scale models
• Leveraged PyTorch Distributed Data Parallel (DDP) on a multi-node GPU cluster for optimal resource utilization

Benchmarking Spurious Biases in Multimodal LLMs

Technologies Used: PyTorch, Multimodal LLMs, Prompt engineering

• Identify and formulate spurious biases in multimodal LLMs
• Design prompts to generate vision-question answers for benchmarking multimodal LLMs

Mitigating Spurious Biases in Deep Image Classifiers

Technologies Used: PyTorch, Vision-language models, ResNet

• Created an automatic spurious bias detection method using vision-language models
• Enhanced model robustness through meta-learning and balanced training; published findings at KDD and IJCAI

Doctor of Philosophy

University of Virginia

Computer Science

Master of Engineering

University of Science and Technology of China

Electrical Engineering

Bachelor of Science

Sun Yat-Sen University

Electrical Engineering

AAAI 2024 Scholarship and Volunteer

AAAI Conference on Artificial Intelligence

SDM 2023 Travel Award

SIAM International Conference on Data Mining

ICDM 2022 Travel Award

IEEE International Conference on Data Mining

Computer Science Fellowship

University of Virginia

MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs

Wenqian Ye, Guangtao Zheng, Yunsheng Ma, Xu Cao, Bolin Lai, James M Rehg, Aidong Zhang

arXiv preprint, 2024.

Fast Clustering and Cell-Type Annotation of scATAC Data Using Pre-trained Embeddings

Nathan J LeRoy, Jason P Smith, Guangtao Zheng, Julia Rymuza, Erfaneh Gharavi, Donald E Brown, Aidong Zhang, Nathan C Sheffield

Nucleic Acids Research Genomics and Bioinformatics (NARGAB), 2024.

Methods for Evaluating Unsupervised Vector Representations of Genomic Regions

Guangtao Zheng, Julia Rymuza, Erfaneh Gharavi, Nathan J LeRoy, Aidong Zhang, Nathan C Sheffield

Nucleic Acids Research Genomics and Bioinformatics (NARGAB), 2024.

Methods for Constructing and Evaluating Consensus Genomic Interval Sets

Julia Rymuza, Yuchen Sun, Guangtao Zheng, Nathan J LeRoy, Maria Murach, Neil Phan, Aidong Zhang, Nathan C Sheffield

Nucleic Acids Research (NAR), 2024.

Spuriousness-Aware Meta-Learning for Learning Robust Classifiers

Guangtao Zheng, Wenqian Ye, Aidong Zhang

The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024.

Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation

Guangtao Zheng, Wenqian Ye, Aidong Zhang

The 33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024.

Spurious Correlations in Machine Learning: A Survey

Wenqian Ye, Guangtao Zheng, Xu Cao, Yunsheng Ma, Aidong Zhang

ICML Workshop on Data-Centric Machine Learning Research, 2024.

Benchmarking Spurious Bias in Few-Shot Image Classifiers

Guangtao Zheng, Wenqian Ye, Aidong Zhang

The 18th European Conference on Computer Vision (ECCV), 2024.

Joint Representation Learning for Retrieval and Annotation of Genomic Interval Sets

Erfaneh Gharavi, Nathan J LeRoy, Guangtao Zheng, Aidong Zhang, Donald E Brown, Nathan C Sheffield

Bioengineering, 2024.

AdvST: Revisiting Data Augmentations for Single Domain Generalization

Guangtao Zheng, Mengdi Huai, Aidong Zhang

The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.

Learning to Learn Task Transformations for Improved Few-Shot Classification

Guangtao Zheng, Qiuling Suo, Mengdi Huai, Aidong Zhang

SIAM International Conference on Data Mining (SDM), 2023.

Knowledge-Guided Semantics Adjustment for Improved Few-Shot Classification

Guangtao Zheng, Aidong Zhang

IEEE International Conference on Data Mining (ICDM), 2022.

Few-Shot Class-Incremental Learning with Meta-Learned Class Structures

Guangtao Zheng, Aidong Zhang

IEEE International Conference on Data Mining (ICDM) Workshop, 2021.

Embeddings of Genomic Region Sets Capture Rich Biological Associations in Lower Dimensions

Erfaneh Gharavi, Aaron Gu, Guangtao Zheng, Jason P Smith, Hyun Jae Cho, Aidong Zhang, Donald E Brown, Nathan C Sheffield

Bioinformatics, 2021.

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection

Hanjie Chen, Guangtao Zheng, Yangfeng Ji

The 58th Annual Meeting of the Association for Computational Linguistics (ACL), 2020.