Zobrazeno 1 - 10
of 945
pro vyhledávání: '"Xu Jinhui"'
To improve persistence diagram representation learning, we propose Multiset Transformer. This is the first neural network that utilizes attention mechanisms specifically designed for multisets as inputs and offers rigorous theoretical guarantees of p
Externí odkaz:
http://arxiv.org/abs/2411.14662
We study the problem of fitting the high dimensional sparse linear regression model with sub-Gaussian covariates and responses, where the data are provided by strategic or self-interested agents (individuals) who prioritize their privacy of data disc
Externí odkaz:
http://arxiv.org/abs/2410.13046
Machine Unlearning has emerged as a significant area of research, focusing on 'removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning, as they effec
Externí odkaz:
http://arxiv.org/abs/2410.03833
Complex networks, which are the abstractions of many real-world systems, present a persistent challenge across disciplines for people to decipher their underlying information. Recently, hyperbolic geometry of latent spaces has gained traction in netw
Externí odkaz:
http://arxiv.org/abs/2405.16928
Continual learning, focused on sequentially learning multiple tasks, has gained significant attention recently. Despite the tremendous progress made in the past, the theoretical understanding, especially factors contributing to catastrophic forgettin
Externí odkaz:
http://arxiv.org/abs/2405.17583
In this paper, we study a generalization of the classical Voronoi diagram, called clustering induced Voronoi diagram (CIVD). Different from the traditional model, CIVD takes as its sites the power set $U$ of an input set $P$ of objects. For each subs
Externí odkaz:
http://arxiv.org/abs/2404.18906
In this paper, we revisit the problem of sparse linear regression in the local differential privacy (LDP) model. Existing research in the non-interactive and sequentially local models has focused on obtaining the lower bounds for the case where the u
Externí odkaz:
http://arxiv.org/abs/2310.07367
Recent text-to-image generation models have demonstrated impressive capability of generating text-aligned images with high fidelity. However, generating images of novel concept provided by the user input image is still a challenging task. To address
Externí odkaz:
http://arxiv.org/abs/2305.13579
We present Corgi, a novel method for text-to-image generation. Corgi is based on our proposed shifted diffusion model, which achieves better image embedding generation from input text. Unlike the baseline diffusion model used in DALL-E 2, our method
Externí odkaz:
http://arxiv.org/abs/2211.15388
Text-to-image generation models have progressed considerably in recent years, which can now generate impressive realistic images from arbitrary text. Most of such models are trained on web-scale image-text paired datasets, which may not be affordable
Externí odkaz:
http://arxiv.org/abs/2210.14124