15 papers
KuaFu: Compressing Long User Behavior into Understanding at Billion Scale
Jiahao Hui, Lin Zhu, Yishen Hu +8
Learning user preferences from long behavioral sequences is fundamental to large-scale advertising, recommender systems, and conversational agents. In industrial systems, preferenc…
ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling
Chengkai Huang, Yubin Sheng, Liang Guo +9
Modeling ultra-long user behavior sequences is crucial for industrial recommendation and online advertising, yet directly feeding thousands of historical actions into ranking model…
Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising
Zipeng Chen, Jiaer Zheng, Xiangyang Xu +15
Recent advances in LLM-based user simulation have shown promise for offline evaluation of recommendation and advertising systems. However, existing simulators typically infer user…
NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems
Shaohua Liu, Liang Fang, Yilong Sun +16
Industrial advertising recommender systems are continually improved through architecture modifications, yet production iteration remains expert-intensive because coordinated change…
Diffusion Language Model for Recommendation
Chengyi Liu, Yongqi Zhou, Junwei Pan +8
Large language model (LLM)-empowered recommender systems have emerged as a promising paradigm for generative recommendation, leveraging their strong semantic reasoning and generati…
SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling
Yaqian Zhang, Ruyi Yu, Tianyi Li +13
Industrial recommender systems increasingly leverage lifelong user behavior histories and rich multi-modal content to capture evolving user preferences. However, effectively integr…
Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
Guoming Li, Shangyu Zhang, Junwei Pan +7
Scaling recommendation models is a central challenge in recommender systems. Recently, RankMixer has emerged as an effective solution, operating on a unified token representation a…
RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems
Jin Chen, Shangyu Zhang, Bin Hu +16
The scaling laws for recommender systems have been increasingly validated, where MetaFormer-based architectures consistently benefit from increased model depth, hidden dimensionali…
Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hierarchical Quantization
Bin Huang, Xin Wang, Junwei Pan +6
Generative Recommendation (GenRec) models reformulate recommendation as a sequence generation task, representing items as discrete Semantic IDs used symmetrically as both inputs an…
TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds
Yifeng Zhou, Yuehong Hu, Zhixiang Feng +9
Recommender systems have historically developed along two largely independent paradigms: feature interaction models for modeling correlations among multi-field categorical features…
Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation
Junwei Pan, Wei Xue, Chao Zhou +20
Generative recommender systems are rapidly emerging as a new paradigm for recommendation, where collaborative identifiers and/or multi-modal content are mapped into discrete token…
An Efficient Embedding Based Ad Retrieval with GPU-Powered Feature Interaction
Yifan Lei, Jiahua Luo, Tingyu Jiang +7
In large-scale advertising recommendation systems, retrieval serves as a critical component, aiming to efficiently select a subset of candidate ads relevant to user behaviors from…
Practice on Long Behavior Sequence Modeling in Tencent Advertising
Xian Hu, Ming Yue, Zhixiang Feng +24
Long-sequence modeling has become an indispensable frontier in recommendation systems for capturing users' long-term preferences. However, user behaviors within advertising domains…
Large Foundation Model for Ads Recommendation
Shangyu Zhang, Shijie Quan, Zhongren Wang +30
Online advertising relies on accurate recommendation models, with recent advances using pre-trained large-scale foundation models (LFMs) to capture users' general interests across…
LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System
Fengxin Li, Yi Li, Yue Liu +11
Display advertising provides significant value to advertisers, publishers, and users. Traditional display advertising systems utilize a multi-stage architecture consisting of retri…