Zobrazeno 1 - 10
of 48 585
pro vyhledávání: '"Wang Kai"'
Autor:
Zhao, Wangbo, Han, Yizeng, Tang, Jiasheng, Wang, Kai, Song, Yibing, Huang, Gao, Wang, Fan, You, Yang
Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference paradigm,
Externí odkaz:
http://arxiv.org/abs/2410.03456
Autor:
Duan, Yifan, Zhao, Jian, pengcheng, Mao, Junyuan, Wu, Hao, Xu, Jingyu, wang, shilong, Ma, Caoyuan, Wang, Kai, Wang, Kun, Li, Xuelong
Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in n
Externí odkaz:
http://arxiv.org/abs/2409.19608
The gravitational wave (GW) event GW190521, likely originating from a binary black hole (BBH) merger within an active galactic nucleus (AGN) disk, is associated with the optical flare ZTF19abanrhr. The remnant BHs from BBH mergers can launch the jet
Externí odkaz:
http://arxiv.org/abs/2409.18567
This paper proposes a model predictive controller for discrete-time linear systems with additive, possibly unbounded, stochastic disturbances and subject to chance constraints. By computing a polytopic probabilistic positively invariant set for const
Externí odkaz:
http://arxiv.org/abs/2409.13032
Autor:
Chen, Dongwei, Wang, Kai-Hsiang
This paper generalizes the least square method to probabilistic approximation in reproducing kernel Hilbert spaces. We show the existence and uniqueness of the optimizer. Furthermore, we generalize the celebrated representer theorem in this setting,
Externí odkaz:
http://arxiv.org/abs/2409.11679
Autor:
Sun, Xunda, Wang, Xin, Ma, Xiangcheng, Wang, Kai, Wetzel, Andrew, Faucher-Giguère, Claude-André, Hopkins, Philip F., Kereš, Dušan, Graf, Russell L., Marszewski, Andrew, Stern, Jonathan, Sun, Guochao, Sun, Lei, Thyme, Keyer
Using the FIRE-2 cosmological zoom-in simulations, we investigate the temporal evolution of gas-phase metallicity radial gradients of Milky Way-mass progenitors in the redshift range of $0.4
Externí odkaz:
http://arxiv.org/abs/2409.09290
Comparing datasets is a fundamental task in machine learning, essential for various learning paradigms; from evaluating train and test datasets for model generalization to using dataset similarity for detecting data drift. While traditional notions o
Externí odkaz:
http://arxiv.org/abs/2409.06997
Dataset distillation (DD) aims to distill a small, information-rich dataset from a larger one for efficient neural network training. However, existing DD methods struggle with long-tailed datasets, which are prevalent in real-world scenarios. By inve
Externí odkaz:
http://arxiv.org/abs/2408.14506
We present Pyramid Attention Broadcast (PAB), a real-time, high quality and training-free approach for DiT-based video generation. Our method is founded on the observation that attention difference in the diffusion process exhibits a U-shaped pattern
Externí odkaz:
http://arxiv.org/abs/2408.12588
Autor:
Zhao, Dingyi, Peng, Yingjie, Jing, Yipeng, Yang, Xiaohu, Ho, Luis C., Renzini, Alvio, Gallazzi, Anna R., Lyu, Cheqiu, Maiolino, Roberto, Dou, Jing, Gao, Zeyu, Gu, Qiusheng, Mannucci, Filippo, Mo, Houjun, Wang, Bitao, Wang, Enci, Wang, Kai, Wang, Yu-Chen, Xu, Bingxiao, Yuan, Feng, Zhu, Xingye
In $\Lambda$CDM cosmology, galaxies form and evolve in their host dark matter (DM) halos. Halo mass is crucial for understanding the halo-galaxy connection. The abundance matching (AM) technique has been widely used to derive the halo masses of galax
Externí odkaz:
http://arxiv.org/abs/2408.12442