Zobrazeno 1 - 10
of 79 775
pro vyhledávání: '"Weimin An"'
Recently, backdoor attack has become an increasing security threat to deep neural networks and drawn the attention of researchers. Backdoor attacks exploit vulnerabilities in third-party pretrained models during the training phase, enabling them to b
Externí odkaz:
http://arxiv.org/abs/2410.12955
Diffusion models have demonstrated exceptional ability in modeling complex image distributions, making them versatile plug-and-play priors for solving imaging inverse problems. However, their reliance on large-scale clean datasets for training limits
Externí odkaz:
http://arxiv.org/abs/2410.11241
Autor:
Song, Yifan, Xiong, Weimin, Zhao, Xiutian, Zhu, Dawei, Wu, Wenhao, Wang, Ke, Li, Cheng, Peng, Wei, Li, Sujian
Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In this work, we introduce AgentBank, by far the largest trajectory tunin
Externí odkaz:
http://arxiv.org/abs/2410.07706
Autor:
Lyu, Weimin, Yao, Jiachen, Gupta, Saumya, Pang, Lu, Sun, Tao, Yi, Lingjie, Hu, Lijie, Ling, Haibin, Chen, Chao
The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing importance, the secu
Externí odkaz:
http://arxiv.org/abs/2410.01264
The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities.
Externí odkaz:
http://arxiv.org/abs/2409.19232
Observation of Transient Trion Induced by Ultrafast Charge Transfer in Graphene/MoS2 Heterostructure
Autor:
Wang, Chen, Chen, Yu, Ma, Qiushi, Suo, Peng, Sun, Kaiwen, Cheng, Yifan, Lin, Xian, Liu, Weimin, Ma, Guohong
Van der Waals (Vdw) heterostructures constructed from TMDCs provide an ideal platform for exploring various quasiparticle behaviors, with trion-composed of neutral exciton and charged carrier-being a notable example. There are typically three methods
Externí odkaz:
http://arxiv.org/abs/2409.17752
Autor:
Hu, Guimin, Xin, Yi, Lyu, Weimin, Huang, Haojian, Sun, Chang, Zhu, Zhihong, Gui, Lin, Cai, Ruichu
Multimodal affective computing (MAC) has garnered increasing attention due to its broad applications in analyzing human behaviors and intentions, especially in text-dominated multimodal affective computing field. This survey presents the recent trend
Externí odkaz:
http://arxiv.org/abs/2409.07388
This paper investigates the design of analog beamforming at the receiver in millimeter-wave (mmWave) multiple-input multiple-output (MIMO) systems, aided by full digital chains featuring 1-bit ADCs. We advocate utilizing these full digital chains to
Externí odkaz:
http://arxiv.org/abs/2409.06819
Facial movements play a crucial role in conveying altitude and intentions, and facial optical flow provides a dynamic and detailed representation of it. However, the scarcity of datasets and a modern baseline hinders the progress in facial optical fl
Externí odkaz:
http://arxiv.org/abs/2409.05396
Anomaly detection is a crucial task in various domains. Most of the existing methods assume the normal sample data clusters around a single central prototype while the real data may consist of multiple categories or subgroups. In addition, existing m
Externí odkaz:
http://arxiv.org/abs/2408.14498