Zobrazeno 1 - 10
of 3 457
pro vyhledávání: '"Gao, Tian"'
Publikováno v:
J. Phys. Chem. C 123, 23655-23660 (2019)
The different types of magnetism arise mainly from how electrons move and interact with each other. In this work, we show how protons (H$^+$) also exhibit magnetic behavior. We measured the magnetic susceptibility of the ammonium halides and identifi
Externí odkaz:
http://arxiv.org/abs/2405.03163
This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on segment-level predictions, whi
Externí odkaz:
http://arxiv.org/abs/2403.11091
PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning
Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the task horizons
Externí odkaz:
http://arxiv.org/abs/2403.00929
Autor:
Shou, Xiao, Subramanian, Dharmashankar, Bhattacharjya, Debarun, Gao, Tian, Bennet, Kristin P.
Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate event stream
Externí odkaz:
http://arxiv.org/abs/2402.00987
Autor:
Tang, Tao, Wei, Dafeng, Jia, Zhengyu, Gao, Tian, Cai, Changwei, Hou, Chengkai, Jia, Peng, Zhan, Kun, Sun, Haiyang, Fan, Jingchen, Zhao, Yixing, Liu, Fu, Liang, Xiaodan, Lang, Xianpeng, Wang, Yang
The rapid development of the autonomous driving industry has led to a significant accumulation of autonomous driving data. Consequently, there comes a growing demand for retrieving data to provide specialized optimization. However, directly applying
Externí odkaz:
http://arxiv.org/abs/2401.01065
Capturing the underlying structural causal relations represented by Directed Acyclic Graphs (DAGs) has been a fundamental task in various AI disciplines. Causal DAG learning via the continuous optimization framework has recently achieved promising pe
Externí odkaz:
http://arxiv.org/abs/2312.12844
Autor:
Wang, Ruoyu, He, Maokui, Du, Jun, Zhou, Hengshun, Niu, Shutong, Chen, Hang, Yue, Yanyan, Yang, Gaobin, Wu, Shilong, Sun, Lei, Tu, Yanhui, Tang, Haitao, Qian, Shuangqing, Gao, Tian, Wang, Mengzhi, Wan, Genshun, Pan, Jia, Gao, Jianqing, Lee, Chin-Hui
This technical report details our submission system to the CHiME-7 DASR Challenge, which focuses on speaker diarization and speech recognition under complex multi-speaker scenarios. Additionally, it also evaluates the efficiency of systems in handlin
Externí odkaz:
http://arxiv.org/abs/2308.14638
Vision Transformer (ViT) has performed remarkably in various computer vision tasks. Nonetheless, affected by the massive amount of parameters, ViT usually suffers from serious overfitting problems with a relatively limited number of training samples.
Externí odkaz:
http://arxiv.org/abs/2305.07931
Place recognition, an algorithm to recognize the re-visited places, plays the role of back-end optimization trigger in a full SLAM system. Many works equipped with deep learning tools, such as MLP, CNN, and transformer, have achieved great improvemen
Externí odkaz:
http://arxiv.org/abs/2303.01166
Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification. Recently, PDE-solving deep learning methods, such as neural operators, are starting to make an important impact on lear
Externí odkaz:
http://arxiv.org/abs/2301.12095