activity
20242026
collaborators

6 papers

cs.IR2026

Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds

Chenfei Li, Hantao Zhao, Weixi Yao +4

Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recen…

cs.IR2025

DiffGRM: Diffusion-based Generative Recommendation Model

Zhao Liu, Yichen Zhu, Yiqing Yang +7

Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively gene…

cs.IR2024

CRM: Retrieval Model with Controllable Condition

Chi Liu, Jiangxia Cao, Rui Huang +5

Recommendation systems (RecSys) are designed to connect users with relevant items from a vast pool of candidates while aligning with the business goals of the platform. A typical i…

cs.IR2024

QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou

Xinchen Luo, Jiangxia Cao, Tianyu Sun +17

In recent years, with the significant evolution of multi-modal large models, many recommender researchers realized the potential of multi-modal information for user interest modeli…

cs.IR2024

KuaiFormer: Transformer-Based Retrieval at Kuaishou

Chi Liu, Jiangxia Cao, Rui Huang +4

In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of option…

cs.IR2024

RecFlow: An Industrial Full Flow Recommendation Dataset

Qi Liu, Kai Zheng, Rui Huang +15

Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS bench…