5 papers
Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation
Xiaoyu Chen, Ruichen Wang, Jieming Di +21
Modeling of long history data suffers from long-context window attention dilution, system efficiency and catastrophic forgetting problems, where naive linear scaling approach like…
Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale
Jieming Di, Xiaoyu Chen, Ying She +21
Large-scale ranking systems depend on thousands of features derived from user behavior across multiple time horizons. Typically requires model retraining -- resulting in long itera…
LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation
Lee Xiong, Zhirong Chen, Rahul Mayuranath +17
We present LLaTTE (LLM-Style Latent Transformers for Temporal Events), a scalable transformer architecture for production ads recommendation. Through systematic experiments, we dem…
ORBIT -- Open Recommendation Benchmark for Reproducible Research with Hidden Tests
Jingyuan He, Jiongnan Liu, Vishan Vishesh Oberoi +7
Recommender systems are among the most impactful AI applications, interacting with billions of users every day, guiding them to relevant products, services, or information tailored…
Group-Level Data Selection for Efficient Pretraining
Zichun Yu, Fei Peng, Jie Lei +3
In this paper, we introduce Group-MATES, an efficient group-level data selection approach to optimize the speed-quality frontier of language model pretraining. Specifically, Group-…