Zobrazeno 1 - 10
of 1 679
pro vyhledávání: '"Li, YuYang"'
Autor:
Zhao, Zihang, Li, Wanlin, Li, Yuyang, Liu, Tengyu, Li, Boren, Wang, Meng, Du, Kai, Liu, Hangxin, Zhu, Yixin, Wang, Qining, Althoefer, Kaspar, Zhu, Song-Chun
Developing robotic hands that adapt to real-world dynamics remains a fundamental challenge in robotics and machine intelligence. Despite significant advances in replicating human hand kinematics and control algorithms, robotic systems still struggle
Externí odkaz:
http://arxiv.org/abs/2412.14482
Autor:
Wang, Cunshi, Hu, Xinjie, Zhang, Yu, Chen, Xunhao, Du, Pengliang, Mao, Yiming, Wang, Rui, Li, Yuyang, Wu, Ying, Yang, Hang, Li, Yansong, Wang, Beichuan, Mu, Haiyang, Wang, Zheng, Tian, Jianfeng, Ge, Liang, Mao, Yongna, Li, Shengming, Lu, Xiaomeng, Zou, Jinhang, Huang, Yang, Sun, Ningchen, Zheng, Jie, He, Min, Bai, Yu, Jin, Junjie, Wu, Hong, Shang, Chaohui, Liu, Jifeng
With the rapid advancements in Large Language Models (LLMs), LLM-based agents have introduced convenient and user-friendly methods for leveraging tools across various domains. In the field of astronomical observation, the construction of new telescop
Externí odkaz:
http://arxiv.org/abs/2412.06412
Statistics of excitations play an essential role in understanding phases of matter. In this paper, we introduce a universal method for studying the generalized statistics of Abelian particles and extended excitations in lattices of any dimension. We
Externí odkaz:
http://arxiv.org/abs/2412.01886
As terrestrial resources become increasingly depleted, the demand for deep-sea resource exploration has intensified. However, the extreme conditions in the deep-sea environment pose significant challenges for underwater operations, necessitating the
Externí odkaz:
http://arxiv.org/abs/2410.16762
Autor:
Turkcan, Mehmet Kerem, Li, Yuyang, Zang, Chengbo, Ghaderi, Javad, Zussman, Gil, Kostic, Zoran
We introduce Boundless, a photo-realistic synthetic data generation system for enabling highly accurate object detection in dense urban streetscapes. Boundless can replace massive real-world data collection and manual ground-truth object annotation (
Externí odkaz:
http://arxiv.org/abs/2409.03022
Autor:
Du, Kaile, Zhou, Yifan, Lyu, Fan, Li, Yuyang, Xie, Junzhou, Shen, Yixi, Hu, Fuyuan, Liu, Guangcan
Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only achieve subo
Externí odkaz:
http://arxiv.org/abs/2408.12161
Parallel Continual Learning (PCL) tasks investigate the training methods for continual learning with multi-source input, where data from different tasks are learned as they arrive. PCL offers high training efficiency and is well-suited for complex mu
Externí odkaz:
http://arxiv.org/abs/2407.08214
Autor:
Li, Puhao, Liu, Tengyu, Li, Yuyang, Han, Muzhi, Geng, Haoran, Wang, Shu, Zhu, Yixin, Zhu, Song-Chun, Huang, Siyuan
Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, modern methods (e.g., VIP and R3M) still face significant hurdles, notably the domain gap am
Externí odkaz:
http://arxiv.org/abs/2404.17521
Autor:
Ding, Kairui, Chen, Boyuan, Wu, Ruihai, Li, Yuyang, Zhang, Zongzheng, Gao, Huan-ang, Li, Siqi, Zhou, Guyue, Zhu, Yixin, Dong, Hao, Zhao, Hao
Robotic manipulation with two-finger grippers is challenged by objects lacking distinct graspable features. Traditional pre-grasping methods, which typically involve repositioning objects or utilizing external aids like table edges, are limited in th
Externí odkaz:
http://arxiv.org/abs/2404.03634
The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unavailable. This issue leads to a proliferation of false-positive errors
Externí odkaz:
http://arxiv.org/abs/2403.12559