Mingxuan (Clark) Ju

110 110th Ave NE

Bellevue, WA 98004, USA

I am a Senior Research Scientist in the User Modeling & Personalization team at Snap Research. My primary focuses include generative recommendation and agentic user understanding.

Before joining Snap, I earned a Ph.D. degree in Computer Science and Engineering from the University of Notre Dame in 2024, advised by Dr. Fanny Ye. Prior to my Ph.D., I received my B.S. and M.S. from Case Western Reserve University, supervised by Dr. Soumya Ray with a focus on machine learning.

I am actively seeking research interns and university collaborations (funded or unfunded) in the space of IR and LLM. Feel free to reach out and I will get back to you asap if there is an alignment.

Besides research, I enjoy fishing, cooking, video games, and photography — take a look at the life page.

You can reach me at mju [at] snap [dot] com (work) or mju2 [at] alumni [dot] nd [dot] edu.

news

Jul 01, 2026	Two papers are accepted to RecSys 26! One studies optimizing textual decoding tries in LLM-based generative recommendation and the other studies ID-text complementarity in sequential recommendation. Congrats to Jingzhe and Liam!
May 01, 2026	One paper that studies the scaling behavior of generative recommenders is accepted to KDD 26. Congrats to Jingzhe! See you in Korea.
Apr 15, 2026	Three papers are accepted to ACL 26! One studies attention sink for LLMs, one studies embedding extraction for decoder-only LLMs, and the other studies agentic user memory management for LLM-RecSys. See you in San Diego!
Apr 01, 2026	One paper about practical deployment of Semantic IDs at Snapchat and another paper that studies multimodal Semantic IDs have been accepted to SIGIR 26. See you in Melbourne!
Oct 20, 2025	Our paper “Generative Recommendation with Semantic IDs: A Practitioner’s Handbook” won the Best Paper Award at CIKM 25! Please take a look at our public repo!

Oct 10, 2025	One paper that studies data augmentation for generative recommendation has been accepted to WSDM 26. Congrats to Geon! See you in Boise.
Oct 01, 2025	We recently released a pre-print studying the scaling laws of generative recommendation! Please take a look and suggestions are welcomed.
Sep 01, 2025	One paper about pre-training on relational databases is accepted to NeurIPS 25. Congrats to Quang! See you in San Diego.
Aug 01, 2025	Our paper entitled “Generative Recommendation with Semantic IDs: A Practitioner’s Handbook” (in short GRID) has been accepted to CIKM 25. GRID is one of the first few public resources that produce state-of-the-art performance using generative recommendation models. Please check out GRID at our public repo!
Jul 01, 2025	One paper about re-ranking using graphs is accepted to RecSys 25. Congrats to Zhongyu!
May 15, 2025	Two papers are accepted to the research track at KDD 25. One paper studies the popularity bias of recommender systems and the other paper studies cross-domain sequential recommendation. See you in Toronto.
May 01, 2025	One paper that studies backward-compatible embedding learning has been accepted to ICML 25. Congrats to Ngoc!
Apr 01, 2025	One paper that studies learning universal user representations leveraging cross-domain user intent has been accepted to the industrial track of SIGIR 25. Thanks for the joint efforts from scientists and engineers at Snapchat. See you in Italy.
Jan 20, 2025	Two papers about RecSys are accepted to WWW 25 and selected as oral presentations. One studies the learning dynamic of RecSys models from the perspective of matrix rank to accelerate the training process; the other studies RecSys model parameter reduction using graph-based hashing methods. Congrats to Donald and Xinyi!
Nov 15, 2024	I defended my Ph.D. dissertation! Thanks for the supports from my advisor and committee members Profs. Fanny Ye, Nitesh Chawla, Walter Scheirer, and Xiangliang Zhang.
Sep 26, 2024	One first-authored paper that studies message passing for collaborative filtering has been accepted to NeurIPS 24. See you in Vancouver.
Aug 15, 2024	Part of my previous work on multi-task self-supervised graph learning has been productionized for EBR retrieval of friend recommendation. Results are published in this manuscript at RobustRecSys@RecSys 2024! Thanks for joint efforts from our engineers and scientists.
Mar 01, 2024	I joined Snap Research as a research scientist.
Sep 22, 2023	One first-authored paper about test-time augmentation for GNNs has been accepted to NeurIPS 23. See you in New Orleans.
Jan 21, 2023	Three papers are accepted to ICLR 23! One first-authored one studies multi-task self-supervised graph learning. The others study large language models for QA and graph adversarial learning. Congrats to everyone involved!
Dec 01, 2022	I will join Snap Research as a research intern for Summer 2023, mentored by Dr. Tong Zhao and Dr. Neil Shah.
Nov 19, 2022	One first-authored paper about graph adversarial attack has been accepted to AAAI 23.
Oct 15, 2022	One first-authored paper on open-domain question answering has been accepted to EMNLP 22. Big thanks to my collaborators and mentors!
Oct 01, 2022	Two amazing pre-prints are now available. One focuses on graph self-supervised learning and the other is about context generation for open-domain QA! Please feel free to contact me if you have any comments or suggestions over the manuscripts.
Jul 01, 2022	I have my personal website now :)

selected publications

RecSys

Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation

Jingzhe Liu, Hanbing Wang, Jiliang Tang, Liam Collins, Tong Zhao, Neil Shah, and Mingxuan Ju

In Proceedings of the 20th ACM Conference on Recommender Systems (RecSys), 2026

Bib

@inproceedings{liu2026tries,
  title = {Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation},
  author = {Liu, Jingzhe and Wang, Hanbing and Tang, Jiliang and Collins, Liam and Zhao, Tong and Shah, Neil and Ju, Mingxuan},
  booktitle = {Proceedings of the 20th ACM Conference on Recommender Systems (RecSys)},
  year = {2026},
}

KDD

Understanding Generative Recommendation with Semantic IDs from a Model-scaling View

Jingzhe Liu, Liam Collins, Jiliang Tang, Tong Zhao, Neil Shah, and Mingxuan Ju

In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026

arXiv Bib

@inproceedings{liu2026scaling,
  title = {Understanding Generative Recommendation with Semantic IDs from a Model-scaling View},
  author = {Liu, Jingzhe and Collins, Liam and Tang, Jiliang and Zhao, Tong and Shah, Neil and Ju, Mingxuan},
  booktitle = {Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
  year = {2026},
}

SIGIR

Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices

Mingxuan Ju^*, Tong Zhao^*, Leonardo Neves, Liam Collins, Bhuvesh Kumar, Jiwen Ren, Lili Zhang, Wenfeng Zhuo, Vincent Zhang, Xiao Bai, Jinchao Li, Karthik Iyer, Zihao Fan, Yilun Xu, Yiwen Chen, Peicheng Yu, Manish Malik, and Neil Shah

In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2026

arXiv Bib

@inproceedings{ju2026semanticids,
  title = {Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices},
  author = {Ju, Mingxuan and Zhao, Tong and Neves, Leonardo and Collins, Liam and Kumar, Bhuvesh and Ren, Jiwen and Zhang, Lili and Zhuo, Wenfeng and Zhang, Vincent and Bai, Xiao and Li, Jinchao and Iyer, Karthik and Fan, Zihao and Xu, Yilun and Chen, Yiwen and Yu, Peicheng and Malik, Manish and Shah, Neil},
  booktitle = {Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
  year = {2026},
}

CIKM

Generative Recommendation with Semantic IDs: A Practitioner’s Handbook

Mingxuan Ju, Liam Collins, Leonardo Neves, Bhuvesh Kumar, Yufeng Wang, Tong Zhao, and Neil Shah

In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM), 2025

Best Paper Award arXiv Bib Code

Best Paper Award at CIKM 2025

@inproceedings{ju2025grid,
  title = {Generative Recommendation with Semantic IDs: A Practitioner's Handbook},
  author = {Ju, Mingxuan and Collins, Liam and Neves, Leonardo and Kumar, Bhuvesh and Wang, Yufeng and Zhao, Tong and Shah, Neil},
  booktitle = {Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM)},
  year = {2025},
}

KDD

Revisiting Self-Attention for Cross-Domain Sequential Recommendation

Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar, Liam Collins, Tong Zhao, Yuwei Qiu, Ching Dou, Sohail Nizam, Sen Yang, and Neil Shah

In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025

arXiv Bib Code

@inproceedings{ju2025autocdsr,
  title = {Revisiting Self-Attention for Cross-Domain Sequential Recommendation},
  author = {Ju, Mingxuan and Neves, Leonardo and Kumar, Bhuvesh and Collins, Liam and Zhao, Tong and Qiu, Yuwei and Dou, Ching and Nizam, Sohail and Yang, Sen and Shah, Neil},
  booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
  year = {2025},
}

SIGIR

Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat

Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar, Liam Collins, Tong Zhao, Yuwei Qiu, Ching Dou, Yang Zhou, Sohail Nizam, Rengim Ozturk, Yvette Liu, Sen Yang, Manish Malik, and Neil Shah

In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2025

arXiv Bib

@inproceedings{ju2025userrep,
  title = {Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat},
  author = {Ju, Mingxuan and Neves, Leonardo and Kumar, Bhuvesh and Collins, Liam and Zhao, Tong and Qiu, Yuwei and Dou, Ching and Zhou, Yang and Nizam, Sohail and Ozturk, Rengim and Liu, Yvette and Yang, Sen and Malik, Manish and Shah, Neil},
  booktitle = {Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
  year = {2025},
}

WWW

Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank

Donald Loveland, Xinyi Wu, Danai Koutra, Tong Zhao, Neil Shah, and Mingxuan Ju

In Proceedings of the ACM Web Conference (WWW), 2025

arXiv Bib

@inproceedings{loveland2025matrixrank,
  title = {Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank},
  author = {Loveland, Donald and Wu, Xinyi and Koutra, Danai and Zhao, Tong and Shah, Neil and Ju, Mingxuan},
  booktitle = {Proceedings of the ACM Web Conference (WWW)},
  year = {2025},
}

NeurIPS

How Does Message Passing Improve Collaborative Filtering?

Mingxuan Ju, William Shiao, Zhichun Guo, Yanfang Ye, Yozen Liu, Neil Shah, and Tong Zhao

In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

arXiv Bib Code

@inproceedings{ju2024messagepassing,
  title = {How Does Message Passing Improve Collaborative Filtering?},
  author = {Ju, Mingxuan and Shiao, William and Guo, Zhichun and Ye, Yanfang and Liu, Yozen and Shah, Neil and Zhao, Tong},
  booktitle = {Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2024},
}

NeurIPS

GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

Mingxuan Ju, Tong Zhao, Wenhao Yu, Neil Shah, and Yanfang Ye

In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS), 2023

arXiv Bib PDF Code

@inproceedings{ju2023graphpatcher,
  title = {GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation},
  author = {Ju, Mingxuan and Zhao, Tong and Yu, Wenhao and Shah, Neil and Ye, Yanfang},
  booktitle = {Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2023},
}

ICLR

Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization

Mingxuan Ju, Tong Zhao, Qianlong Wen, Wenhao Yu, Neil Shah, Yanfang Ye, and Chuxu Zhang

In Proceedings of the 11th International Conference on Learning Representations (ICLR), 2023

Bib HTML Code

@inproceedings{ju2023paretognn,
  title = {Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization},
  author = {Ju, Mingxuan and Zhao, Tong and Wen, Qianlong and Yu, Wenhao and Shah, Neil and Ye, Yanfang and Zhang, Chuxu},
  booktitle = {Proceedings of the 11th International Conference on Learning Representations (ICLR)},
  year = {2023},
}

AAAI

Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning

Mingxuan Ju, Yujie Fan, Chuxu Zhang, and Yanfang Ye

In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023

arXiv Bib Code

@inproceedings{ju2023goboard,
  title = {Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning},
  author = {Ju, Mingxuan and Fan, Yujie and Zhang, Chuxu and Ye, Yanfang},
  booktitle = {Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
}

EMNLP

Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

Mingxuan Ju^*, Wenhao Yu^*, Tong Zhao, Chuxu Zhang, and Yanfang Ye

In Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

arXiv Bib Code

@inproceedings{ju2022grape,
  title = {Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering},
  author = {Ju, Mingxuan and Yu, Wenhao and Zhao, Tong and Zhang, Chuxu and Ye, Yanfang},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022},
  year = {2022},
}

SDM

Heterogeneous Temporal Graph Neural Network

Yujie Fan, Mingxuan Ju, Chuxu Zhang, Liang Zhao, and Yanfang Ye

In Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), 2022

Bib HTML Code

@inproceedings{fan2022htgnn,
  title = {Heterogeneous Temporal Graph Neural Network},
  author = {Fan, Yujie and Ju, Mingxuan and Zhang, Chuxu and Zhao, Liang and Ye, Yanfang},
  booktitle = {Proceedings of the 2022 SIAM International Conference on Data Mining (SDM)},
  year = {2022},
}

AAAI

Adaptive Kernel Graph Neural Network

Mingxuan Ju, Shifu Hou, Yujie Fan, Jianan Zhao, Liang Zhao, and Yanfang Ye

In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI), 2022

Bib PDF Code

@inproceedings{ju2022akgnn,
  title = {Adaptive Kernel Graph Neural Network},
  author = {Ju, Mingxuan and Hou, Shifu and Fan, Yujie and Zhao, Jianan and Zhao, Liang and Ye, Yanfang},
  booktitle = {Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
}

WWW

Dr. Emotion: Disentangled Representation Learning for Emotion Analysis on Social Media to Improve Community Resilience in the COVID-19 Era and Beyond

Mingxuan Ju, Wei Song, Shiyu Sun, Yanfang Ye, Yujie Fan, Shifu Hou, Kenneth Loparo, and Liang Zhao

In Proceedings of the Web Conference (WWW), 2021

Best Paper Shortlist Bib HTML Code

Best Paper Award Shortlist at WWW 2021

@inproceedings{ju2021dremotion,
  title = {Dr. Emotion: Disentangled Representation Learning for Emotion Analysis on Social Media to Improve Community Resilience in the COVID-19 Era and Beyond},
  author = {Ju, Mingxuan and Song, Wei and Sun, Shiyu and Ye, Yanfang and Fan, Yujie and Hou, Shifu and Loparo, Kenneth and Zhao, Liang},
  booktitle = {Proceedings of the Web Conference (WWW)},
  year = {2021},
}