About me

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.

News

[2026.4] 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!

[2026.4] 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!

[2025.10] 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!

[2025.10] One paper that studies data augmentation for generative recommendation has been accepted to WSDM'25. Congrats to Geon! See you in Boise.

[2025.10] We recently released a pre-print studying the scaling laws of generative recommendation! Please take a look and suggestions are welcomed.

[2025.09] One paper about pre-training on relational databases is accepted to NeurIPS'25. Congrats to Quang! See you in San Diego.

[2025.08] 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!

[2025.05] 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.

[2025.04] 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.

[2025.07] One paper about re-ranking using graphs is accepted to RecSys'25. Congrats to Zhongyu!

[2025.05] One paper that studies backward-compatible embedding learning has been accepted to ICML'25. Congrats to Ngoc!

[2025.01] Two papers about RecSys are accepted to WWW 2025 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!

[2024.11] I defended my Ph.D. dissertation! Thanks for the supports from my advisor and committe members Profs. Fanny Ye, Nitesh Chawla, Walter Scheirer, and Xiangliang Zhang.

[2024.09] One first-authored paper that studies message passing for collaborative filtering has been accepted to NeurIPS'24. See you in Vancouver.

[2024.08] Part of my previous work on multi-task self-suerpvised graph learning has been productionized for EBR retrieval of friend recommendation. Results are published in this manuscript at RobustRecSysRecSys2024! Thanks for joint efforts from our engineers and scientists.

[2024.03] I joined Snap Research as a research scientist.

[2023.09] One first-authored paper about test-time augmentation for GNNs has been accepted to NeurIPS'23. See you in New Orleans.

[2023.01] Three papers are accepted to ICLR'23! One first-authored one studies multi-task self-suerpvised graph learning. The others study large language models for QA and graph adversarial learning. Congrats to everyone involved!

[2022.12] I will join Snap Research as a research intern for Summar 2023, mentored by Dr. Tong Zhao and Dr. Neil Shah.

[2022.11] One first-authored paper about graph adversarial attack has been accepted to AAAI'23.

[2022.10] One first-authored paper on open-domain question answering has been accepted to EMNLP'22. Big thanks to my collaborators and mentors!

[2022.10] 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.

[2022.07] I have my personal website now :)

Preprint(s):

Understanding Generative Recommendation with Semantic IDs from a Model-scaling View
J. Liu, L. Collins, J. Tang, T. Zhao, N. Shah, M. Ju
arXiv [pdf]
Enhancing Item Tokenization for Generative Recommendation through Self-Improvement
R. Chen, M. Ju, N. Bui, D. Antypas, S. Cai, X. Wu, L. Neves, Z. Wang, N. Shah, T. Zhao
arXiv [pdf]
Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation
Y. Hou, H. Kim, M. Ju, E. Escoto, N. Shah, J. McAuley arXiv [pdf]

Selected Publications

[Full List] [Google Scholar]

Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices
M. Ju*, T. Zhao*, L. Neves, L. Collins, B. Kumar, J. Ren, L. Zhang, W. Zhuo, V. Zhang, X. Bai, J. Li, K. Iyer, Z. Fan, Y. Xu, Y. Chen, P. Yu, M Malik, N. Shah
SIGIR 26 [pdf]
Generative Recommendation with Semantic IDs: A Practitioner’s Handbook
M. Ju, L. Collins, L. Neves, B. Kumar, Y. Wang, T. Zhao, N. Shah
CIKM 25 (Best Paper Award)[pdf] [code]
Revisiting Self-attention for Cross-domain Sequential Recommendation
M. Ju, L. Neves, B. Kumar, L. Collins, T. Zhao, Y. Qiu, C. Dou, S. Nizam, S. Yang, N. Shah
KDD 25 [pdf] [code]
Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat
M. Ju, L. Neves, B. Kumar, L. Collins, T. Zhao, Y. Qiu, C. Dou, Y. Zhou, S. Nizam, R. Ozturk, Y. Liu, S. Yang, M. Malik, N. Shah
SIGIR 25 [pdf]
Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank
D. Loveland, X. Wu, T. Zhao, D. Koutra, N. Shah, M. Ju
WWW 25 [pdf]
How Does Message Passing Improve Collaborative Filtering?
M. Ju, W. Shiao, Z. Guo, Y. Ye, Y. Liu, N. Shah, T. Zhao
NeurIPS 24 [pdf] [code]
GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
M. Ju, T. Zhao, W. Yu, N. Shah, Y. Ye
NeurIPS 23 [pdf] [code]
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
M. Ju, T. Zhao, Q. Wen, W. Yu, N. Shah, Y. Ye, C. Zhang
ICLR 23 [pdf] [code]
Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning
M. Ju, Y. Fan, C. Zhang, Y. Ye
AAAI 23 [pdf] [code]
Grape: Knowledge Graph Enhance Passage Reader for Open-domain Question Answering
M. Ju*, W. Yu*, T. Zhao, C. Zhang, Y. Ye
EMNLP 22 (Findings) [pdf] [code]
Adaptive Kernel Graph Neural Network
M. Ju, S. Hou, Y. Fan, J. Zhao, Y. Ye, L. Zhao
AAAI 22 [pdf] [code]

* stands for equal contribution.

Contact

Snap Email: mju [at] snap [dot] com
ND Alumni Email: mju2 [at] alumni [dot] nd [dot] edu
Location: 110 110th Ave NE, Bellevue, WA

Clark Mingxuan Ju

News Show More

Preprint(s):

Selected Publications

Contact

News