MetaSR
The official implementation of a meta-learning framework that bridges next-item prediction and masked-language modeling for recommendation.
Personalization and retrieval
We study sequential and multimodal recommendation: how models represent user intent, adapt foundation models efficiently, preserve useful cross-modal signals, and balance relevance with discovery. This area connects peer-reviewed papers to the official implementations and reproducibility resources maintained by their authors.
The official implementation of a meta-learning framework that bridges next-item prediction and masked-language modeling for recommendation.
A benchmark for measuring how multimodal language models reconstruct missing product text or imagery and support recommendation.
Frequency-decoupled knowledge distillation for reducing multimodal recommendation cost while preserving useful cross-modal signals.
A decoupled parameter-efficient adaptation framework for symmetric and asymmetric multimodal foundation models in recommendation.
An open implementation for aligning language-model recommenders with both relevance and serendipity objectives.
Y Li, E Ni, Y Liu, et al.
Z Zhuang, H Du, H Han, et al.
J Fu, Y Ni, JM Jose, et al.
J Fu, X Ge, X Xin, et al.
Z Zhuang, H Li, J Fu, et al.
Jiayang Wang, Yihan Liu, Hongji Li, et al.
Z Yuan, L Sun, Y Zhuang, et al.
H Li, H Du, Y Li, et al.
Y Li, H Du, Y Ni, et al.