About Me

I’m a Research Scientist at Snap Research on the User Modeling and Personalization (UMaP) team led by Neil Shah. My current research focuses on LLM-based and generative recommendation systems, personalization, sequential recommendation, retrieval, and representation learning.

I completed my PhD at UT Austin under the supervision of Aryan Mokhtari and Sanjay Shakkottai, and studied in-context learning, multi-task learning and feature learning theory. Prior to this I earned a B.S.E. from Princeton where I worked under Yuxin Chen.

My email is lcollins2 at snap dot com.

[Last update: July 2026]

News

Papers

Please see my Google Scholar profile for the most updated list of papers.

On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies Sunwoo Kim, Sunkyung Lee, Clark Mingxuan Ju, Donald Loveland, Bhuvesh Kumar, Kijung Shin, Neil Shah, LC arXiv preprint, 2026 [PDF]

Implicit Reasoning for Large Language Model-based Generative Recommendation
Yinhan He, LC, Bhuvesh Kumar, Jundong Li, Neil Shah, Donald Loveland
arXiv preprint, 2026
[PDF]

CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
Hansi Zeng, LC, Bhuvesh Kumar, Neil Shah, Hamed Zamani
arXiv preprint, 2026
[PDF] [Code]

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings
Xueying Ding, Xingyue Huang, Clark Ju, LC, Yozen Liu, Leman Akoglu, Neil Shah, Tong Zhao
ACL 2026
[PDF]

Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices
Clark Mingxuan Ju*, Tong Zhao*, Leonardo Neves, LC, 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, Neil Shah
* equal contributions
SIGIR 2026
[PDF] [Code]

Sequential Data Augmentation for Generative Recommendation
Geon Lee, Bhuvesh Kumar, Clark Ju, Tong Zhao, Kijung Shin, Neil Shah, LC
WSDM 2026
[PDF] [Code]

Understanding Generative Recommendation with Semantic IDs from a Model-scaling View
Jingzhe Liu, LC, Jiliang Tang, Tong Zhao, Neil Shah, Clark Ju
KDD 2026
[PDF]

Masked Diffusion for Generative Recommendation
Kulin Shah, Bhuvesh Kumar, Neil Shah, LC
arXiv preprint, 2025
[PDF] [Code]

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation
LC, Bhuvesh Kumar, Clark Ju, Tong Zhao, Donald Loveland, Leonardo Neves, Neil Shah
arXiv preprint, 2025
[PDF]

Generative Recommendation with Semantic IDs: A Practitioner’s Handbook
Clark Ju, LC, Leonardo Neves, Bhuvesh Kumar, Louis Wang, Tong Zhao, Neil Shah
CIKM 2025 Best Paper Award
[PDF] [Code]

Revisiting Self-Attention for Cross-Domain Sequential Recommendation
Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar, LC, Tong Zhao, Yuwei Qiu, Qing Dou, Sohail Nizam, Sen Yang, Neil Shah
KDD 2025
[PDF] [Code]

Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat
Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar, LC, Tong Zhao, Yuwei Qiu, Qing Dou, Yang Zhou, Sohail Nizam, Rengim Ozturk, Yvette Liu, Sen Yang, Manish Malik, Neil Shah
SIGIR 2025 Industry Track
[PDF]