Dongliang Guo

Applied Scientist at Amazon · AI Researcher

I work on trustworthy foundation AI, multimodal learning, language models, and agentic AI systems. I completed my Ph.D. in Data Science at the University of Virginia in 2026, advised by Sheng Li.

donglgcn@gmail.com Google Scholar GitHub LinkedIn

Research

Trustworthy AIMultimodal LearningFoundation Models

Model editing, fairness and trustworthy representation learning, explainable anomaly detection, and reliable evaluation of foundation-model-based systems.

Experience

Amazon · Applied Scientist

Agentic systems for Amazon Sellers and Specialists.

Seattle, WA
Jun. 2026 – Present

Amazon · Applied Scientist Intern

Unified multimodal tokenization for customer, behavioral, and order-related signals.

Seattle, WA
May – Aug. 2025

Amazon · Applied Scientist Intern

Multimodal language-model approaches for user request understanding and order decisions.

Seattle, WA
May – Aug. 2024

Amazon · Applied Scientist Intern

Multimodal fraud detection with CLIP-style alignment of tabular and textual data.

Seattle, WA
May – Aug. 2023

Selected Publications

† Equal contribution

The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning

Wenqian Ye, Luyang Jiang, Eric Xie, Guangtao Zheng, Yunsheng Ma, Xu Cao, Dongliang Guo, et al.

TMLR 2026

Paper

Instruction-based Time Series Editing

Jiaxing Qiu, Dongliang Guo, Brynne Sullivan, Teague R. Henry, Thomas Hartvigsen

KDD 2026

Paper

Revisiting Dynamic Graphs from the Perspective of Time Series

Weili Shi, Dongliang Guo, Sheng Li

TMLR 2026

Paper

Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding

Daiqing Qi†, Dongliang Guo†, Hanzhang Yuan, Handong Zhao, Mengxuan Hu, Lehan Yang, Sheng Li

NeurIPS 2025

Paper

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users

Mengxuan Hu†, Hongyi Wu†, Ronghang Zhu, Zihan Guan, Dongliang Guo, Daiqing Qi, Sheng Li

Findings of EMNLP 2025

Paper

Few-shot Fine-grained Image Classification with Interpretable Prompt Learning through Distribution Alignment

Dongliang Guo, Handong Zhao, Ryan A. Rossi, Sungchul Kim, Nedim Lipka, Tong Yu, Sheng Li

ICMI 2025

Paper

BalancEdit: Dynamically Balancing the Generality–Locality Trade-off in Multi-modal Model Editing

Dongliang Guo, Mengxuan Hu, Zihan Guan, Thomas Hartvigsen, Sheng Li

ICML 2025

Paper Code

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing

Dongliang Guo†, Mengxuan Hu†, Zihan Guan, Junfeng Guo, Thomas Hartvigsen, Sheng Li

CIKM 2025

Paper Code

Ada-VAD: Domain Adaptable Video Anomaly Detection

Dongliang Guo, Yun Fu, Sheng Li

SDM 2024

Paper Code

Fair Attribute Completion on Graph with Missing Attributes

Dongliang Guo, Zhixuan Chu, Sheng Li

ICLR 2023

Paper Code

Explainable anomaly detection survey figure

Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos

Yizhou Wang†, Dongliang Guo†, Sheng Li, Octavia Camps, Yun Fu

Under review at IEEE TPAMI

Paper Code

Trustworthy representation learning survey figure

A Survey of Trustworthy Representation Learning Across Domains

Ronghang Zhu, Dongliang Guo, Daiqing Qi, Zhixuan Chu, Xiang Yu, Sheng Li

ACM TKDD 2024

Paper

Education

University of Virginia

Ph.D. in Data Science · Advisor: Sheng Li

Aug. 2023 – Apr. 2026

University of Georgia

Ph.D. in Computer Science · Advisor: Sheng Li

Aug. 2021 – Aug. 2023

University of Electronic Science and Technology of China

B.E. in Software Engineering

Sep. 2016 – Jun. 2020

Service

Program Chair, NeurIPS 2024 Workshop on Large Foundation Models for Educational Assessment. 88 completed reviews across 24 venues, including NeurIPS, ICLR, ICML, AAAI, COLM, SDM, TMLR, and IEEE TNNLS.