Zobrazeno 1 - 10
of 119
pro vyhledávání: '"Chen, Zhenhao"'
Autor:
Song, Zirui, Ouyang, Guangxian, Fang, Meng, Na, Hongbin, Shi, Zijing, Chen, Zhenhao, Fu, Yujie, Zhang, Zeyu, Jiang, Shiyu, Fang, Miao, Chen, Ling, Chen, Xiuying
Existing household robots have made significant progress in performing routine tasks, such as cleaning floors or delivering objects. However, a key limitation of these robots is their inability to recognize potential problems or dangers in home envir
Externí odkaz:
http://arxiv.org/abs/2411.00781
Recently, there has been a surge of interest in developing graph neural networks that utilize the invariance principle on graphs to generalize the out-of-distribution (OOD) data. Due to the limited knowledge about OOD data, existing approaches often
Externí odkaz:
http://arxiv.org/abs/2407.11083
Autonomous virtual agents are often limited by their singular mode of interaction with real-world environments, restricting their versatility. To address this, we propose the Multi-Modal Agent Collaboration framework (MMAC-Copilot), a framework utili
Externí odkaz:
http://arxiv.org/abs/2404.18074
The recent success of Large Language Models (LLMs) has catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs, attempting to address the ong
Externí odkaz:
http://arxiv.org/abs/2402.12563
Autor:
Chen, Guangyi, Shen, Yifan, Chen, Zhenhao, Song, Xiangchen, Sun, Yuewen, Yao, Weiran, Liu, Xiao, Zhang, Kun
Identifying the underlying time-delayed latent causal processes in sequential data is vital for grasping temporal dynamics and making downstream reasoning. While some recent methods can robustly identify these latent causal variables, they rely on st
Externí odkaz:
http://arxiv.org/abs/2401.14535
Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles. However, their robustness against diverse style shifts, crucial for practical applications, remains largely unexp
Externí odkaz:
http://arxiv.org/abs/2312.02896
Publikováno v:
CVPR 2023
The indeterminate nature of human motion requires trajectory prediction systems to use a probabilistic model to formulate the multi-modality phenomenon and infer a finite set of future trajectories. However, the inference processes of most existing m
Externí odkaz:
http://arxiv.org/abs/2304.04298
Autor:
Huang, Qiaoying, Zhang, Bo, Wang, Dan, Zhao, Min, Chen, Lei, Yang, Xiaojing, Yang, Yabing, Wang, Miao, Chen, Zhenhao, Zhang, Zhike, Qin, Yonghua, Zhao, Jietang, Hu, Guibing
Publikováno v:
In Scientia Horticulturae 1 May 2024 331
Autor:
Zhou, Yi, Chen, Zhenhao
Memes are used for spreading ideas through social networks. Although most memes are created for humor, some memes become hateful under the combination of pictures and text. Automatically detecting the hateful memes can help reduce their harmful socia
Externí odkaz:
http://arxiv.org/abs/2011.12870
Autor:
Wu, Jianwei, Chen, Zhenhao, Wang, Hongwei, Tian, Ye, Ma, Xiaosheng, Lyu, Feizhou, Jiang, Jianyuan, Wang, Hongli
Publikováno v:
In World Neurosurgery January 2023 169:e102-e109