← Latest papers
🤖 machine learning

Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts

The paper introduces DUMoE, a unified framework that leverages a temporal dynamics-aware backbone and a sparse mixture-of-experts adapter with a three-stage training strategy to effectively model multi-scale temporal patterns and disentangle diverse, drifting user interests for improved representation learning on social media.

Original authors: Ziqing Qian, Haohang Chen, Shengqi Dang, Yuhan Xiong, Canyu Shen, Jiaying Lei, Nan Cao

Published 2026-08-27
📖 1 min read☕ Coffee break read

Original authors: Ziqing Qian, Haohang Chen, Shengqi Dang, Yuhan Xiong, Canyu Shen, Jiaying Lei, Nan Cao

Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer

Drowning in papers in your field?

Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.

Try Digest →