Hugging Face Trending Papers

Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment

Read the original on Hugging Face Trending Papers →

In multi-source ECG deployment, models may need to incorporate new data sources when earlier raw ECGs cannot be retained or replayed. Freezing a pretrained backbone and assigning each source an isolated classifier prevents parameter interference, but deployment still requires selecting an expert when source metadata are unavailable.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 11

UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models

arXiv:2608. 08627v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes over its full expert bank.

By Lei Xin, Bin Gu, Peize Li, Zitong Wang, Jianbo Zhao, Changjiang Jiang, Yanyue Xie, Chao Huang, Xuyang Zhao, Zunhai Su, Fanhu Zeng, Zhenglun Kong
arXiv Machine Learning
Jul 24

PreMoE: Proactive Inference for Efficient Mixture-of-Experts

arXiv:2505. 17639v4 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization.

By Zehua Pei, Ying Zhang, Hui-Ling Zhen, Tao Yuan, Xianzhi Yu, Zhenhua Dong, Sinno Jialin Pan, Mingxuan Yuan, Bei Yu