Yiyue Qian

Yiyue Qian

I am a Founding Applied Scientist at Model Customization Team, AWS Generative AI Innovation Center, working on GenAI model customization, post-training, LLM evaluation, agentic AI systems, multimodal learning, and graph representation learning.

Email / Resume / Google Scholar / LinkedIn / Github

News

Jul. 2026: I will travel to San Diego to attend the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026). Happy to chat in San Diego!

2026: Our work Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification was accepted to the International Workshop on Resource-Efficient Learning for Knowledge Discovery, colocated with KDD 2026.
2026: Our paper OPBench: A Graph Benchmark to Combat the Opioid Crisis was accepted to KDD 2026.
2026: Our paper N-Mars: Non-Monotonic Autoregressive Sequence Model was accepted to ICML 2026.
2025: Our paper LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection was accepted to ACL Findings 2025.
2025: Our paper Enhancing E-commerce Representation Learning via Hypergraph Contrastive Learning and Interpretable LLM-Driven Analysis was accepted to WWW 2025.
Mar. 2025: I traveled to Philadelphia to present our work Enhancing LLM-as-a-Judge via Multi-Agent Collaboration at the AAAI 2025 Workshop on Advancing LLM-Based Multi-Agent Collaboration.
2025: Our paper Enhancing LLM-as-a-Judge via Multi-Agent Collaboration was accepted to AAAI 2025 WMAC.
2025: Our paper AutoData: A Multi-Agent System for Open Web Data Collection was accepted to NeurIPS 2025.
2026: Our work Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification was accepted to the International Workshop on Resource-Efficient Learning for Knowledge Discovery, colocated with KDD 2026.
2026: Our paper OPBench: A Graph Benchmark to Combat the Opioid Crisis was accepted to KDD 2026.
2026: Our paper N-Mars: Non-Monotonic Autoregressive Sequence Model was accepted to ICML 2026.

Experience

Amazon AWS, Generative AI Innovation Center, Applied Scientist II, Tech Lead, Founding Scientist at Model Customization Team, Seattle USA, Dec 2023 - present.

Focus Domains: Post-training, Continual Pre-training, Agent Customization, Agentic AI, Physical AI, World Model.

Amazon, Applied Scientist Intern, Seattle USA, May 2023 - Sept. 2023; May 2022 - Aug. 2022.

Focus Domains: LLM Finetuning, Model Pretraining, Multi-modal Learning, Graph Learning, Fraud Detection, Marketplace Integrity.

PingAn Technology, NLP Algorithm Engineer, Shenzhen China, Jan. 2018- Aug. 2019.

Focus Domains: Natural Language Processing, Name Entity Recognition, Sentiment Analysis, Risk Event Detection, Financial NLP.

Education

University of Notre Dame, PhD in Computer Science and Engineering, South Bend，USA, Jan. 2022 - Dec. 2023

Case Western Reserve University, PhD in Computer Science and Engineering, Cleveland，USA, Sept. 2019 - Dec. 2021.

University College London, Master in Statistics, London， UK, Sept. 2016- Sept. 2017.

Research

General: Artificial Intelligence, Generative AI, Physical AI, Deep Learning, Machine Learning, Data Mining

Research Direction: Post-training, Continual Pre-training, Agent Customization, Agentic AI, Physical AI, World Model, LLM Evaluation, Multi-modal Learning, Graph Representation Learning, Hypergraph Learning, Contrastive Learning

Application: Generative AI, Customized Model Deployment, Agents Development and Deployment, MCP Deployment

Publication

	Non-Monotonic Autoregressive Sequence Model Tianyi Ma, Yiyue Qian, Yiyang Li, Zehong Wang, Yifan Ding, Zheyuan Zhang, Yan Liang, Chuxu Zhang, Yanfang Ye. [ICML'26] The Forty-third International Conference on Machine Learning [Reinforcement Learning, Sequence Modeling, Autoregressive Models] code
	OPBench: A Graph Benchmark to Combat the Opioid Crisis Tianyi Ma, Yiyang Li, Yiyue Qian, Zheyuan Zhang, Zehong Wang, Chuxu Zhang, Yanfang Ye. [KDD'26] The ACM SIGKDD Conference on Knowledge Discovery and Data Mining [Graph Benchmark, Opioid Crisis, Public Safety, Graph Learning] code
	Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification Yiyue Qian, Shinan Zhang, Huan Song, Negin Sokhandan, Hannah Marlowe, Diego Socolinsky. [KDD RelKD'26] International Workshop on Resource-Efficient Learning for 2026 ACM SIGKDD Conference on Knowledge Discovery and Data Mining [Dynamic In-Context Learning, LLM, Agentic AI, Schema Classification]
	AutoData: A Multi-Agent System for Open Web Data Collection Yiyue Qian, Tianyi Ma, Zheyuan Zhang, Zehong Wang, Xiaoye Qian, Feifan Bai, Yifan Ding, Xuwei Luo, Shinan Zhang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye. [NeurIPS'25] The Conference on Neural Information Processing Systems [Agentic AI, Multi-agent Systems, Open Web Data Collection, Data Curation] code
	Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models Huan Song, Deeksha Razdan, Yiyue Qian, Arijit Ghosh Chowdhury, Parth Patwa, Aman Chadha, Shinan Zhang, Sharlina Keshava, Hannah Marlowe. [NeurIPS'25 Workshop] The Conference on Neural Information Processing Systems 2025 Workshop on Post-Training and Continual Learning for AI Agents [Data Augmentation, Fine-Tuning, Evaluation, Small Language Models]
	Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors Henger Li, Shuangjie You, Flavio Di Palo, Yiyue Qian, Ayush Jain. [WWW'25 Workshop] The International World Wide Web Conference 2025 Workshop on LLMs as Editors: Enhancing LLM Performance through Iterative Refinement [Tool Calling, Context Optimization, Hierarchical LLMs-as-Editors]
	LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection Tianyi Ma, Yiyue Qian, Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye. [ACL'25] The 63rd Annual Meeting of the Association for Computational Linguistics project page [LLM, Graph Prompt Learning, Imbalanced Learning, Public Safety]
	Enhancing E-commerce Representation Learning via Hypergraph Contrastive Learning and Interpretable LLM-Driven Analysis Yiyue Qian, Shinan Zhang, Lanhao Chen, Diego Socolinsky, Negin Sokhandan, Song Cui, De Chen, Suchitra Sathyanarayana. [WWW'25] The International World Wide Web Conference [E-commerce, Hypergraph Learning, Contrastive Learning, LLM Analysis]
	Enhancing LLM-as-a-Judge via Multi-Agent Collaboration Yiyue Qian, Shinan Zhang, Yun Zhou, Haibo Ding, Diego Socolinsky, Yi Zhang. [AAAI'25 WMAC] The Association for the Advancement of Artificial Intelligence 2025 Workshop on Advancing LLM-Based Multi-Agent Collaboration [LLM-as-a-Judge, Multi-agent Systems, Evaluation]
	Adaptive Graph Enhancement for Imbalanced Multi-relation Graph Learning Yiyue Qian, Tianyi Ma, Chuxu Zhang, and Yanfang Ye. [WSDM'25] The International Conference on Web Search and Data Mining project page [Graph Learning, Imbalanced Learning, Multi-relation Graphs]
	Dual-level Hypergraph Contrastive Learning with Adaptive Temperature Enhancement Yiyue Qian, Tianyi Ma, Chuxu Zhang, and Yanfang Ye. [WWW'24] The International World Wide Web Conference project page [Hypergraph Learning, Contrastive Learning, Adaptive Temperature]
	Hypergraph Contrastive Learning for Drug Trafficking Community Detection Tianyi Ma, Yiyue Qian, Chuxu Zhang, and Yanfang Ye. (co-first author) [ICDM'23] The IEEE International Conference on Data Mining project page [Hypergraph Learning, Contrastive Learning, Drug Trafficking Detection]
	Co-modality graph contrastive learning for imbalanced node classification Yiyue Qian, Chunhui Zhang, Yiming Zhang, Qianlong Wen, Yanfang Ye, and Chuxu Zhang. [NeurIPS'22] The Conference on Neural Information Processing Systems project page [Multi-modal Learning, Graph Contrastive Learning, Imbalanced Learning]
	Rep2Vec: Repository Embedding via Heterogeneous Graph Adversarial Contrastive Learning Yiyue Qian, Yiming Zhang, Qianlong Wen, Yanfang Ye, and Chuxu Zhang. [KDD'22] The ACM SIGKDD Conference on Knowledge Discovery and Data Mining [Heterogeneous Graphs, Adversarial Learning, Repository Mining]
	Malicious Repositories Detection with Adversarial Heterogeneous Graph Contrastive Learning Yiyue Qian, Yiming Zhang, Yanfang Ye, and Chuxu Zhang. [CIKM'22] The ACM Conference on Information and Knowledge Management [Cybersecurity, Heterogeneous Graphs, Contrastive Learning]
	Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media Yiyue Qian, Yiming Zhang, Yanfang Ye, and Chuxu Zhang. [NeurIPS'21] The Conference on Neural Information Processing Systems github [Meta Learning, Heterogeneous Graphs, Public Safety]
	Adapting Meta Knowledge with Heterogeneous Information Network for COVID-19 Themed Malicious Repository Detection Yiyue Qian, Yiming Zhang, Yanfang Ye, and Chuxu Zhang. [IJCAI'21] The International Joint Conference on Artificial Intelligence [Cybersecurity, Heterogeneous Graphs, Few-shot Learning]
	Adapting Distilled Knowledge for Few-shot Relation Reasoning over Knowledge Graphs Yiming Zhang, Yiyue Qian, Yanfang Ye, and Chuxu Zhang. [SDM'22] The SIAM International Conference on Data Mining [Knowledge Graphs, Few-shot Learning, Relation Reasoning]
	dstyle-gan: Generative adversarial network based on writing and photography styles for drug identification in darknet markets Yiming Zhang, Yiyue Qian, Yanfang Ye, and Chuxu Zhang. [ACSAC'20] The Annual Computer Security Applications Conference [Generative Models, Darknet Markets, Public Safety]
	Disentangled Dynamic Heterogeneous Graph Learning for Opioid Overdose Prediction Qianlong Wen, Zhongyu Ouyang, Jianfei Zhang, Yiyue Qian , Yanfang Ye, and Chuxu Zhang. [KDD'22] The ACM SIGKDD Conference on Knowledge Discovery and Data Mining [Dynamic Graphs, Healthcare AI, Public Safety]
	α-Satellite: An AI-driven System and Benchmark Datasets for Hierarchical Community-level Risk Assessment to Help Combat COVID-19 Yanfang Ye, Shifu Hou, Yujie Fan, Yiyue Qian, Yiming Zhang, Shiyu Sun, Qian Peng, Kenneth Laparo [JBHI'20] IEEE Journal of Biomedical and Health Informatics [Healthcare AI, Risk Assessment, Public Safety]
	Community mitigation: A data-driven system for covid-19 risk assessment in a hierarchical manner Yanfang Ye, Yujie Fan, Shifu Hou, Yiming Zhang, Yiyue Qian, Shiyu Sun, Qian Peng, Mingxuan Ju, Wei Song, Kenneth Loparo [CIKM'20] The ACM International Conference on Information and Knowledge Management [Data Mining, Risk Assessment, Public Safety]

Award

Best Paper Award, The Web Conference (WWW) Workshop, 2025

Best Paper Award Candidate, ICDM, 2025

NeurIPS Scholar Award, 2022

CIKM Student Travel Award, 2022

Service

Area Chair: PKDD'26.

Senior Program Committee: CIKM'24, CIKM'25.

Conference Program Committee Member: KDD'22, ICDM'22, WWW'22, AAAI'23, KDD'23, IJCAI'23, NeurIPS'23, AAAI'24, SDM'24, ICLR'24, WWW'24, ICML'24, KDD'24, WWW'25, WSDM'25, KDD'25, NeurIPS'25, CIKM'25.

Journal Reviewer: The Journal of Neurocomputing, IEEE Transactions on Big Data, IEEE Transactions on Dependable and Secure Computing, ACM Transactions on Privacy and Security, IEEE Transactions on Neural Networks and Learning Systems.

Outreach Program Judge: Learning Science Sphere Event at Northpoint Elementary School in 2023

Teaching

Teaching assistant of computer security (CSE-40567, CSDS 344)

Hobbies

Skiing

Travelling

Hiking

Diving

Badminton

Ping Pong

Yoga

"Life is all about balance. You don't always need to be getting stuff done. Sometimes it's perfectly okay, and absolutely necessary, to shut down, kick back, and do nothing."