Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Park, Dahoon"'
To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper, we present
Externí odkaz:
http://arxiv.org/abs/2409.05902
When training early-stage deep neural networks (DNNs), generating intermediate features via convolution or linear layers occupied most of the execution time. Accordingly, extensive research has been done to reduce the computational burden of the conv
Externí odkaz:
http://arxiv.org/abs/2211.02686
In this paper, we present Zero-data Based Repeated bit flip Attack (ZeBRA) that precisely destroys deep neural networks (DNNs) by synthesizing its own attack datasets. Many prior works on adversarial weight attack require not only the weight paramete
Externí odkaz:
http://arxiv.org/abs/2111.01080
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Park, Dahoon1 (AUTHOR), Kim, Yushin1 (AUTHOR) kimy@cju.ac.kr
Publikováno v:
Scientific Reports. 5/27/2023, Vol. 13 Issue 1, p1-9. 9p.
Autor:
Nancy Snow, Nicholas J. Cull
The second edition of the Routledge Handbook of Public Diplomacy, co-edited by two leading scholars in the international relations subfield of public diplomacy, includes 16 more chapters from the first. Ten years later, a new global landscape of publ