4 citations · 8 across the 4 of their papers we have counts for
4 papers
Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples
Kuofeng Gao, Jindong Gu, Yang Bai +4
Despite the exceptional performance of multi-modal large language models (MLLMs), their deployment requires substantial computational resources. Once malicious users induce high en…
IMUOptimize: A Data-Driven Approach to Optimal IMU Placement for Human Pose Estimation with Transformer Architecture
Varun Ramani, Hossein Khayami, Yang Bai +2
This paper presents a novel approach for predicting human poses using IMU data, diverging from previous studies such as DIP-IMU, IMUPoser, and TransPose, which use up to 6 IMUs in…
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Kuofeng Gao, Yang Bai, Jindong Gu +4
Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial e…
Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks
Xiaojun Jia, Jianshu Li, Jindong Gu +2
Adversarial training has shown promise in building robust models against adversarial examples. A major drawback of adversarial training is the computational overhead introduced by…