Zobrazeno 1 - 10
of 59 814
pro vyhledávání: '"Liu,Xin"'
Ensembles of generative large language models (LLMs) can integrate the strengths of different LLMs to compensate for the limitations of individual models. However, recent work has focused on training an additional fusion model to combine complete res
Externí odkaz:
http://arxiv.org/abs/2412.07380
This paper addresses the challenge of spectral-spatial feature extraction for hyperspectral image classification by introducing a novel tensor-based framework. The proposed approach incorporates circular convolution into a tensor structure to effecti
Externí odkaz:
http://arxiv.org/abs/2412.06075
Autor:
Liu, Shanqi, Liu, Xin
This paper studies online convex optimization with unknown linear budget constraints, where only the gradient information of the objective and the bandit feedback of constraint functions are observed. We propose a safe and efficient Lyapunov-optimiza
Externí odkaz:
http://arxiv.org/abs/2412.03983
Autor:
Merz, Grant, Liu, Xin, Schmidt, Samuel, Malz, Alex I., Zhang, Tianqing, Branton, Doug, Burke, Colin J., Delucchi, Melissa, Ejjagiri, Yaswant Sai, Kubica, Jeremy, Liu, Yichen, Lynn, Olivia, Oldag, Drew, Collaboration, The LSST Dark Energy Science
Photometric redshifts will be a key data product for the Rubin Observatory Legacy Survey of Space and Time (LSST) as well as for future ground and space-based surveys. The need for photometric redshifts, or photo-zs, arises from sparse spectroscopic
Externí odkaz:
http://arxiv.org/abs/2411.18769
6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues effectivel
Externí odkaz:
http://arxiv.org/abs/2411.17174
Pre-training Transformer models is resource-intensive, and recent studies have shown that sign momentum is an efficient technique for training large-scale deep learning models, particularly Transformers. However, its application in distributed traini
Externí odkaz:
http://arxiv.org/abs/2411.17866
Autor:
Zhuang, Chen, Chen, Peng, Liu, Xin, Yokota, Rio, Dryden, Nikoli, Endo, Toshio, Matsuoka, Satoshi, Wahib, Mohamed
Graph Convolutional Networks (GCNs) are widely used in various domains. However, training distributed full-batch GCNs on large-scale graphs poses challenges due to inefficient memory access patterns and high communication overhead. This paper present
Externí odkaz:
http://arxiv.org/abs/2411.16025
Remote photoplethysmography (rPPG) extracts PPG signals from subtle color changes in facial videos, showing strong potential for health applications. However, most rPPG methods rely on intensity differences between consecutive frames, missing long-te
Externí odkaz:
http://arxiv.org/abs/2411.15283
In computer vision, estimating the six-degree-of-freedom pose from an RGB image is a fundamental task. However, this task becomes highly challenging in multi-object scenes. Currently, the best methods typically employ an indirect strategy, which iden
Externí odkaz:
http://arxiv.org/abs/2411.14002
Autor:
Liu, Xin-Yang, Parikh, Meet Hemant, Fan, Xiantao, Du, Pan, Wang, Qing, Chen, Yi-Fan, Wang, Jian-Xun
Eddy-resolving turbulence simulations require stochastic inflow conditions that accurately replicate the complex, multi-scale structures of turbulence. Traditional recycling-based methods rely on computationally expensive precursor simulations, while
Externí odkaz:
http://arxiv.org/abs/2411.14378