Zobrazeno 1 - 10
of 9 362
pro vyhledávání: '"ZENG, Yi"'
Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is critical for g
Externí odkaz:
http://arxiv.org/abs/2410.04190
As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this balance. Exist
Externí odkaz:
http://arxiv.org/abs/2410.02298
Human beings often experience stress, which can significantly influence their performance. This study explores whether Large Language Models (LLMs) exhibit stress responses similar to those of humans and whether their performance fluctuates under dif
Externí odkaz:
http://arxiv.org/abs/2409.17167
The hierarchical architecture has become a mainstream design paradigm for Vision Transformers (ViTs), with Patch Merging serving as the pivotal component that transforms a columnar architecture into a hierarchical one. Drawing inspiration from the br
Externí odkaz:
http://arxiv.org/abs/2409.06963
Systolic architectures are widely embraced by neural network accelerators for their superior performance in highly parallelized computation. The DSP48E2s serve as dedicated arithmetic blocks in Xilinx Ultrascale series FPGAs and constitute a fundamen
Externí odkaz:
http://arxiv.org/abs/2409.03508
We proposed a novel dense line spectrum super-resolution algorithm, the DMRA, that leverages dynamical multi-resolution of atoms technique to address the limitation of traditional compressed sensing methods when handling dense point-source signals. T
Externí odkaz:
http://arxiv.org/abs/2409.00799
Spiking Neural Networks (SNNs), with their brain-inspired structure using discrete spikes instead of continuous activations, are gaining attention for their potential of efficient processing on neuromorphic chips. While current SNN hardware accelerat
Externí odkaz:
http://arxiv.org/abs/2408.15578
Autor:
Zhuang, Shi-Chang, Li, Bo, Zheng, Ming-Yang, Zeng, Yi-Xi, Wu, Hui-Nan, Li, Guang-Bing, Yao, Quan, Xie, Xiu-Ping, Li, Yu-Huai, Qin, Hao, You, Li-Xing, Xu, Fei-Hu, Yin, Juan, Cao, Yuan, Zhang, Qiang, Peng, Cheng-Zhi, Pan, Jian-Wei
The entangled photons are crucial resources for quantum communications and networking. Here, we present an ultra-bright polarization-entangled photon source based on a periodically poled lithium niobate waveguide designed for practical quantum commun
Externí odkaz:
http://arxiv.org/abs/2408.04361
Autor:
He, Xiang, Liu, Xiangxi, Li, Yang, Zhao, Dongcheng, Shen, Guobin, Kong, Qingqun, Yang, Xin, Zeng, Yi
The audio-visual event localization task requires identifying concurrent visual and auditory events from unconstrained videos within a network model, locating them, and classifying their category. The efficient extraction and integration of audio and
Externí odkaz:
http://arxiv.org/abs/2408.01952
Autor:
Zeng, Yi, Yang, Yu, Zhou, Andy, Tan, Jeffrey Ziwei, Tu, Yuheng, Mai, Yifan, Klyman, Kevin, Pan, Minzhou, Jia, Ruoxi, Song, Dawn, Liang, Percy, Li, Bo
Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and safety benchmarks in response. However, existing public benchmarks oft
Externí odkaz:
http://arxiv.org/abs/2407.17436