Zobrazeno 1 - 10
of 2 749
pro vyhledávání: '"WANG Zihan"'
Autor:
Wang, Zihan, Liang, Brian, Dhat, Varad, Brumbaugh, Zander, Walker, Nick, Krishna, Ranjay, Cakmak, Maya
Understanding robot behaviors and experiences through natural language is crucial for developing intelligent and transparent robotic systems. Recent advancement in large language models (LLMs) makes it possible to translate complex, multi-modal robot
Externí odkaz:
http://arxiv.org/abs/2411.12960
As video generation models advance rapidly, assessing the quality of generated videos has become increasingly critical. Existing metrics, such as Fr\'echet Video Distance (FVD), Inception Score (IS), and ClipSim, measure quality primarily in latent s
Externí odkaz:
http://arxiv.org/abs/2411.13609
Retrieval-augmented generation (RAG) has gained wide attention as the key component to improve generative models with external knowledge augmentation from information retrieval. It has shown great prominence in enhancing the functionality and perform
Externí odkaz:
http://arxiv.org/abs/2410.20598
With the development of intelligent connected vehicle technology, human-machine shared control has gained popularity in vehicle following due to its effectiveness in driver assistance. However, traditional vehicle following systems struggle to mainta
Externí odkaz:
http://arxiv.org/abs/2410.18007
Autor:
Zhang, Ronghui, Yang, Shangyu, Lyu, Dakang, Wang, Zihan, Chen, Junzhou, Ren, Yilong, Gao, Bolin, Lv, Zhihan
Road ponding, a prevalent traffic hazard, poses a serious threat to road safety by causing vehicles to lose control and leading to accidents ranging from minor fender benders to severe collisions. Existing technologies struggle to accurately identify
Externí odkaz:
http://arxiv.org/abs/2410.16999
Autor:
Fu, Xiaohan, Li, Shuheng, Wang, Zihan, Liu, Yihao, Gupta, Rajesh K., Berg-Kirkpatrick, Taylor, Fernandes, Earlence
Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems represent an eme
Externí odkaz:
http://arxiv.org/abs/2410.14923
Autor:
Wang, Zihan, Yang, Daniel W., Liu, Zerui, Yan, Evan, Sun, Heming, Ge, Ning, Hu, Miao, Wu, Wei
This study presents the first implementation of multilayer neural networks on a memristor/CMOS integrated system on chip (SoC) to simultaneously detect multiple diseases. To overcome limitations in medical data, generative AI techniques are used to e
Externí odkaz:
http://arxiv.org/abs/2410.14882
Autor:
Lyu, Yougang, Yan, Lingyong, Wang, Zihan, Yin, Dawei, Ren, Pengjie, de Rijke, Maarten, Ren, Zhaochun
As large language models (LLMs) are rapidly advancing and achieving near-human capabilities, aligning them with human values is becoming more urgent. In scenarios where LLMs outperform humans, we face a weak-to-strong alignment problem where we need
Externí odkaz:
http://arxiv.org/abs/2410.07672
Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical research aimed
Externí odkaz:
http://arxiv.org/abs/2410.04887
Recent advancements in 3D Gaussian Splatting (3D-GS) have revolutionized novel view synthesis, facilitating real-time, high-quality image rendering. However, in scenarios involving reflective surfaces, particularly mirrors, 3D-GS often misinterprets
Externí odkaz:
http://arxiv.org/abs/2410.01614