Zobrazeno 1 - 10
of 221
pro vyhledávání: '"Lipman, Yaron"'
Autor:
Gat, Itai, Remez, Tal, Shaul, Neta, Kreuk, Felix, Chen, Ricky T. Q., Synnaeve, Gabriel, Adi, Yossi, Lipman, Yaron
Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this work, we p
Externí odkaz:
http://arxiv.org/abs/2407.15595
Autor:
Shaul, Neta, Singer, Uriel, Chen, Ricky T. Q., Le, Matthew, Thabet, Ali, Pumarola, Albert, Lipman, Yaron
This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a family of non-stationary solvers that provably subsumes existing numerica
Externí odkaz:
http://arxiv.org/abs/2403.01329
Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled generation in gene
Externí odkaz:
http://arxiv.org/abs/2402.14017
Current diffusion or flow-based generative models for 3D shapes divide to two: distilling pre-trained 2D image diffusion models, and training directly on 3D shapes. When training a diffusion or flow models on 3D shapes a crucial design choice is the
Externí odkaz:
http://arxiv.org/abs/2312.09222
Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable improvements for the sample quality, it has only been exclusively employe
Externí odkaz:
http://arxiv.org/abs/2311.13443
Diffusion or flow-based models are powerful generative paradigms that are notoriously hard to sample as samples are defined as solutions to high-dimensional Ordinary or Stochastic Differential Equations (ODEs/SDEs) which require a large Number of Fun
Externí odkaz:
http://arxiv.org/abs/2310.19075
Autor:
Liu, Guan-Horng, Lipman, Yaron, Nickel, Maximilian, Karrer, Brian, Theodorou, Evangelos A., Chen, Ricky T. Q.
Modern distribution matching algorithms for training diffusion or flow models directly prescribe the time evolution of the marginal distributions between two boundary distributions. In this work, we consider a generalized distribution matching setup,
Externí odkaz:
http://arxiv.org/abs/2310.02233
Recent successful generative models are trained by fitting a neural network to an a-priori defined tractable probability density path taking noise to training examples. In this paper we investigate the space of Gaussian probability paths, which inclu
Externí odkaz:
http://arxiv.org/abs/2306.06626
Autor:
Pooladian, Aram-Alexandre, Ben-Hamu, Heli, Domingo-Enrich, Carles, Amos, Brandon, Lipman, Yaron, Chen, Ricky T. Q.
Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, such as Flow Matching, derived paths that are optimal for each data samp
Externí odkaz:
http://arxiv.org/abs/2304.14772
Surface reconstruction has been seeing a lot of progress lately by utilizing Implicit Neural Representations (INRs). Despite their success, INRs often introduce hard to control inductive bias (i.e., the solution surface can exhibit unexplainable beha
Externí odkaz:
http://arxiv.org/abs/2303.14569