Search

News
People
Publications

English
English
中文 (简体)

Jun Zhang

Latest

Draft& Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
Preventing the Popular Item Embedding Based Attack in Federated Recommendations

© 2025 SuDIS-ZJU. This work is licensed under CC BY SA 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.

Cite