Zobrazeno 1 - 10
of 7 468
pro vyhledávání: '"LI, YIMING"'
Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries poison datasets with adversary-specified triggers to implant hidden backdoors, enabling malicious manipulation of model predictions. Dataset purification serves as a p
Externí odkaz:
http://arxiv.org/abs/2411.19479
Large Language Models (LLMs) are vulnerable to backdoor attacks, where hidden triggers can maliciously manipulate model behavior. While several backdoor attack methods have been proposed, the mechanisms by which backdoor functions operate in LLMs rem
Externí odkaz:
http://arxiv.org/abs/2411.12701
Autor:
Ren, Kui, Yang, Ziqi, Lu, Li, Liu, Jian, Li, Yiming, Wan, Jie, Zhao, Xiaodi, Feng, Xianheng, Shao, Shuo
The rapid advancement of AI technology, particularly in generating AI-generated content (AIGC), has transformed numerous fields, e.g., art video generation, but also brings new risks, including the misuse of AI for misinformation and intellectual pro
Externí odkaz:
http://arxiv.org/abs/2411.11478
Generating discharge summaries is a crucial yet time-consuming task in clinical practice, essential for conveying pertinent patient information and facilitating continuity of care. Recent advancements in large language models (LLMs) have significantl
Externí odkaz:
http://arxiv.org/abs/2411.03805
Visual place recognition (VPR) enables autonomous robots to identify previously visited locations, which contributes to tasks like simultaneous localization and mapping (SLAM). VPR faces challenges such as accurate image neighbor retrieval and appear
Externí odkaz:
http://arxiv.org/abs/2410.21615
Reliable object grasping is one of the fundamental tasks in robotics. However, determining grasping pose based on single-image input has long been a challenge due to limited visual information and the complexity of real-world objects. In this paper,
Externí odkaz:
http://arxiv.org/abs/2410.15879
Exploring new knowledge is a fundamental human ability that can be mirrored in the development of deep neural networks, especially in the field of object detection. Open world object detection (OWOD) is an emerging area of research that adapts this p
Externí odkaz:
http://arxiv.org/abs/2410.11301
Autor:
Zhang, Bobing, Zhang, Yiyuan, Li, Yiming, Xuan, Sicheng, Ng, Hong Wei, Liufu, Yuliang, Tang, Zhiqiang, Laschi, Cecilia
Underwater vehicles have seen significant development over the past seventy years. However, bio-inspired propulsion robots are still in their early stages and require greater interdisciplinary collaboration between biologists and roboticists. The oct
Externí odkaz:
http://arxiv.org/abs/2410.11764
Autor:
Li, Boheng, Wei, Yanhao, Fu, Yankai, Wang, Zhenting, Li, Yiming, Zhang, Jie, Wang, Run, Zhang, Tianwei
Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techniques have been proposed to customize the pre-trained base models for
Externí odkaz:
http://arxiv.org/abs/2410.10437
Autor:
Ge, Yifei, Sun, Weisong, Lou, Yihang, Fang, Chunrong, Zhang, Yiran, Li, Yiming, Zhang, Xiaofang, Liu, Yang, Zhao, Zhihong, Chen, Zhenyu
Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software developers. To further improve the performance of LLMs on specific code intel
Externí odkaz:
http://arxiv.org/abs/2410.02841