Lee Xiong

Lee Xiong

Auto-generated profile, based on publicly available information

Lee Xiong

Meta, Menlo Park, CA, USA

Research Focus & Metrics

Representative Publications

View All Publications
22 September 2025
Verified
Conference Paper
Open access
AFAkira Fukumoto
Akira Fukumoto
ASAghiles Salah
Aghiles Salah
SSSarthak Shrivastava
Sarthak Shrivastava
ATAlexandru Tatar
Alexandru Tatar
YSYannick Schwartz
Yannick Schwartz
LXLee Xiong
Lee Xiong

8 August 2026
Verified
Conference Paper
Open access
LXLee Xiong
Lee Xiong
ZCZhirong Chen
Zhirong Chen
RMRahul Mayuranath
Rahul Mayuranath
SQShangran Qiu
Shangran Qiu
AOAhmet Arda Ozdemir
Ahmet Arda Ozdemir
AOArnold Overwijk
Arnold Overwijk
We present LLaTTE (LLM-Style Latent Transformers for Temporal Events), a scalable transformer architecture for production ads recommendation. Through systematic experiments, we demonstrate that sequence modeling in recommendation systems follows predictable power-law scaling similar to LLMs. Crucially, we find that semantic features bend the scaling curve: they are a prerequisite for scaling, enabling the model to effectively utilize the capacity of deeper and longer architectures. To realize the benefits of continued scaling under strict latency constraints, we introduce a two-stage architecture that offloads the heavy computation of large, long-context models to an asynchronous upstream user model. We demonstrate that upstream improvements transfer predictably to downstream ranking tasks. Deployed as the largest user model at Meta, this multi-stage framework drives a 4.3% conversion uplift on Facebook Feed and Reels with minimal serving overhead, establishing a practical blueprint for harnessing scaling laws in industrial recommender systems.

27 September 2026
Verified
Conference Paper
Open access
ZCZhirong Chen
Zhirong Chen
HCHoward Cheng
Howard Cheng
ALAllen Lin
Allen Lin
PDParshva Doshi
Parshva Doshi
YHYang Hu
Yang Hu
LXLee Xiong
Lee Xiong