5 papers
Teacher Retains Full Tokens, Student Merges Efficiently: TM20K for E-Commerce Sequence Modeling in Ad Recommendation
Xinchun Li, Duoru Zheng, Wenlin Zhao +13
Benefiting from ultra-long behavior sequence modeling, existing recommender systems bring users a better experience via simultaneously considering their long-term and short-term in…
Rec-Distill: An Industrial Distillation Pipeline for Large-Scale Recommendation Models
Haoran Ding, Wenlin Zhao, Yuchen Jiang +16
Large recommendation models have demonstrated substantial potential gains under scaling laws, yet these gains are difficult to realize in industrial recommendation systems because…
MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization
Shanlei Mu, Yuchen Jiang, Shikang Wu +7
Industrial recommender systems increasingly adopt multi-scenario learning (MSL) and multi-task learning (MTL) to handle diverse user interactions and contexts, but existing approac…
TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders
Yuchen Jiang, Jie Zhu, Xintian Han +18
While scaling laws for recommendation models have gained significant traction, existing architectures such as Wukong, HiFormer and DHEN, often struggle with sub-optimal designs and…
RankMixer: Scaling Up Ranking Models in Industrial Recommenders
Jie Zhu, Zhifang Fan, Xiaoxie Zhu +18
Recent progress on large language models (LLMs) has spurred interest in scaling up recommendation systems, yet two practical obstacles remain. First, training and serving cost on i…