Zobrazeno 1 - 10
of 11 484
pro vyhledávání: '"Qi LU"'
Autor:
Shi, Qingyu, Qi, Lu, Wu, Jianzong, Bai, Jinbin, Wang, Jingbo, Tong, Yunhai, Li, Xiangtai, Yang, Ming-Husan
Customized image generation is crucial for delivering personalized content based on user-provided image prompts, aligning large-scale text-to-image diffusion models with individual needs. However, existing models often overlook the relationships betw
Externí odkaz:
http://arxiv.org/abs/2410.23280
We present Layout-Your-3D, a framework that allows controllable and compositional 3D generation from text prompts. Existing text-to-3D methods often struggle to generate assets with plausible object interactions or require tedious optimization proces
Externí odkaz:
http://arxiv.org/abs/2410.15391
Spatiotemporal predictive learning methods generally fall into two categories: recurrent-based approaches, which face challenges in parallelization and performance, and recurrent-free methods, which employ convolutional neural networks (CNNs) as enco
Externí odkaz:
http://arxiv.org/abs/2410.04733
Autor:
Qi, Lu
We study the geometry of spaces of fitrations on a Noetherian local domain. We introduce a metric $d_1$ on the space of saturated filtrations, inspired by the Darvas metric in complex geometry, such that it is a geodesic metric space. In the toric ca
Externí odkaz:
http://arxiv.org/abs/2409.01705
Topological flat bands (TFBs) provide a promising platform to investigate intriguing fractionalization phenomena, such as the fractional Chern insulators (FCIs). Most of TFB models are established in two-dimensional Euclidean lattices with zero curva
Externí odkaz:
http://arxiv.org/abs/2408.16615
We prove the ACC conjecture for local volumes. Moreover, when the local volume is bounded away from zero, we prove Shokurov's ACC conjecture for minimal log discrepancies.
Comment: 22 pages, remove the assumption "Q-Gorenstein" in Theorem 1.7
Comment: 22 pages, remove the assumption "Q-Gorenstein" in Theorem 1.7
Externí odkaz:
http://arxiv.org/abs/2408.15090
Autor:
Lin, Xin, Zhou, Yuyan, Yue, Jingtong, Ren, Chao, Chan, Kelvin C. K., Qi, Lu, Yang, Ming-Hsuan
Unsupervised restoration approaches based on generative adversarial networks (GANs) offer a promising solution without requiring paired datasets. Yet, these GAN-based approaches struggle to surpass the performance of conventional unsupervised GAN-bas
Externí odkaz:
http://arxiv.org/abs/2408.09241
The recent surge in Multimodal Large Language Models (MLLMs) has showcased their remarkable potential for achieving generalized intelligence by integrating visual understanding into Large Language Models.Nevertheless, the sheer model size of MLLMs le
Externí odkaz:
http://arxiv.org/abs/2407.19409
Although video perception models have made remarkable advancements in recent years, they still heavily rely on explicit text descriptions or pre-defined categories to identify target instances before executing video perception tasks. These models, ho
Externí odkaz:
http://arxiv.org/abs/2407.14500
Publikováno v:
Phys. Rev. B 110, 195113 (2024)
Fractional Chern insulators (FCIs) have attracted intensive attention for the realization of fractional quantum Hall states in the absence of an external magnetic field. Most of FCIs have been proposed on two-dimensional (2D) Euclidean lattice models
Externí odkaz:
http://arxiv.org/abs/2407.05706