2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency

11 September 2021

Papers citing "2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency"

4 / 4 papers shown

Title
EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting Zhongzhi Yu Zheng Wang Yuhan Li Haoran You Ruijie Gao Xiaoya Zhou Sreenidhi Reedy Bommu Yang Katie Zhao Yingyan Celine Lin 24 12 0 22 Jun 2024
Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning Y. Fu Ye Yuan Shang Wu Jiayi Yuan Yingyan Lin OOD 39 3 0 24 Apr 2023
DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning Mohammad Hossein Samavatian Saikat Majumdar Kristin Barber R. Teodorescu AAML 6 2 0 31 Jul 2022
MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation Zhongzhi Yu Y. Fu Sicheng Li Chaojian Li Yingyan Lin ViT 23 18 0 21 Dec 2021