Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Susskind, Joshua M."'
Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity in the sampled images, particularly when sampling with a high classif
Externí odkaz:
http://arxiv.org/abs/2405.21048
Autor:
Stracke, Nick, Baumann, Stefan Andreas, Susskind, Joshua M., Bautista, Miguel Angel, Ommer, Björn
Text-to-image generative models have become a prominent and powerful tool that excels at generating high-resolution realistic images. However, guiding the generative process of these models to consider detailed forms of conditioning reflecting style
Externí odkaz:
http://arxiv.org/abs/2405.07913
Recent advancements in image generation have made significant progress, yet existing models present limitations in perceiving and generating an arbitrary number of interrelated images within a broad context. This limitation becomes increasingly criti
Externí odkaz:
http://arxiv.org/abs/2404.03109
Autor:
Thilak, Vimal, Huang, Chen, Saremi, Omid, Dinh, Laurent, Goh, Hanlin, Nakkiran, Preetum, Susskind, Joshua M., Littwin, Etai
Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent challenge of evaluating learned representations without access to a do
Externí odkaz:
http://arxiv.org/abs/2312.04000
We present a novel way to predict molecular conformers through a simple formulation that sidesteps many of the heuristics of prior works and achieves state of the art results by using the advantages of scale. By training a diffusion generative model
Externí odkaz:
http://arxiv.org/abs/2311.17932
Autor:
Zhao, Xiaoming, Colburn, Alex, Ma, Fangchang, Bautista, Miguel Angel, Susskind, Joshua M., Schwing, Alexander G.
Rendering scenes observed in a monocular video from novel viewpoints is a challenging problem. For static scenes the community has studied both scene-specific optimization techniques, which optimize on every test scene, and generalized techniques, wh
Externí odkaz:
http://arxiv.org/abs/2310.08587
We present Manifold Diffusion Fields (MDF), an approach that unlocks learning of diffusion models of data in general non-Euclidean geometries. Leveraging insights from spectral geometry analysis, we define an intrinsic coordinate system on the manifo
Externí odkaz:
http://arxiv.org/abs/2305.15586
Autor:
Zhuang, Peiye, Abnar, Samira, Gu, Jiatao, Schwing, Alex, Susskind, Joshua M., Bautista, Miguel Ángel
Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains. However, to adapt diffusion generative modeling to these domains the denoising network needs to be carefully
Externí odkaz:
http://arxiv.org/abs/2303.00165
Autor:
Guo, Pengsheng, Bautista, Miguel Angel, Colburn, Alex, Yang, Liang, Ulbricht, Daniel, Susskind, Joshua M., Shan, Qi
We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects. We propose a simple yet effective approach that is neither continuous nor implicit, challenging recent trends on view synthesis. Our appr
Externí odkaz:
http://arxiv.org/abs/2107.05775
Deep linear networks trained with gradient descent yield low rank solutions, as is typically studied in matrix factorization. In this paper, we take a step further and analyze implicit rank regularization in autoencoders. We show greedy learning of l
Externí odkaz:
http://arxiv.org/abs/2107.01301