Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
Wang, X., et al. (2025). "Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs." International Conference on Machine Learning (ICML).
| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://stephen016.github.io/cv/
access-control-allow-origin: *
strict-transport-security: max-age=31556952
expires: Tue, 30 Dec 2025 11:10:52 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: 940D:2916CC:A0AF06:B45330:6953B0E4
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 11:00:52 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210066-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767092453.552758,VS0,VE222
vary: Accept-Encoding
x-fastly-request-id: c6fad41afd039410bf5aa34cf60ede0dd71f0f62
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 04 Aug 2025 12:59:43 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"6890aebf-2f09"
expires: Tue, 30 Dec 2025 11:10:52 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 5CD3:3ABDEF:9EBA99:B25F43:6953B0E1
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 11:00:53 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210066-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767092453.788338,VS0,VE239
vary: Accept-Encoding
x-fastly-request-id: 2fcea377cb93ab317334e72694f8951eb89c2f07
content-length: 3381
CV - Xun Wang - Xun Wang / Personal Page
CV - Xun Wang
Education
- Ph.D. Student in Computer Science, CISPA Helmholtz Center for Information Security, 2023-Present
- Focus: Machine Learning Security and Privacy
- Co-supervised by Prof. Michael Backes, Prof. Franziska Boenisch, and Prof. Adam Dziedzic
- Member of SprintML Lab
- M.S., Technical University of Munich, 2023
- Graduated with High Distinction
- Thesis: Architecture-Agnostic Neural Network Pruning
Publications
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
Wang, X., et al. (2024). "Structurally Prune Anything: Any Architecture, Any Framework, Any Time." arXiv preprint arXiv:2403.18955.