output
20202026
most citedThe Spectroscopic Binaries from LAMOST Medium-Resolution Survey (MRS). I. Searching for Double-lined Spectroscopic Binaries (SB2s) with Convolutional Neural Network

44 citations

Showing cs.IRShow all

7 papers · 1 filter

cs.IR2026

ConAlign: Conditional Alignment Framework for Balancing Biased and Unbiased Recommendation

Jingcheng Zhang, Yihan Wang, Qi Song +1

Industry recommender systems trained on observational data suffer from various biases that create filter bubbles, causing user interests to collapse into narrow categories and seve…

cs.IR2026

RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation

Ziyi Zhao, Xiaoyou Zhou, Xiao Lv +13

Language-based user profiles convert long behavioral histories into explicit semantic representations for recommendation. However, most profile generators are optimized in an open…

cs.IR2026

Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation

Shiteng Cao, Junda She, Bin Zeng +9

Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a t…

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.IR2025

MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever

Yijia Sun, Shanshan Huang, Linxiao Che +4

Modern industrial recommendation systems encounter a core challenge of multi-stage optimization misalignment: a significant semantic gap exists between the multi-objective optimiza…

cs.IR20249 cited

Modeling User Fatigue for Sequential Recommendation

Nian Li, Xin Ban, Cheng Ling +6

Recommender systems filter out information that meets user interests. However, users may be tired of the recommendations that are too similar to the content they have been exposed…