Hugging Peers

MixEmb: Importance-Aware Quantization and Caching Co-Design for Industrial Decentralized Embedding Training

☆ Save
Jiang, Zhida,Chen, Zhen,Xing, Zhaolong,Wang, Jiaxing,Gao, Saixing,Yuan, Baopeng,Wang, Hao,Xu, Yin
+3 more authors show fewer
Liu, Lin,Wang, Dongyue,Zhang, Ke
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
published

Abstract

No abstract available.

Cite this paper

@article{zhida2026,
  title = {MixEmb: Importance-Aware Quantization and Caching Co-Design for Industrial Decentralized Embedding Training},
  author = {Jiang, Zhida and Chen, Zhen and Xing, Zhaolong and Wang, Jiaxing and Gao, Saixing and Yuan, Baopeng and Wang, Hao and Xu, Yin and Liu, Lin and Wang, Dongyue and Zhang, Ke},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track},
  year = {2026},
  month = {Jan},
}