Zobrazeno 1 - 10
of 6 008
pro vyhledávání: '"P, Heinonen"'
We investigate what kind of images lie in the high-density regions of diffusion models. We introduce a theoretical mode-tracking process capable of pinpointing the exact mode of the denoising distribution, and we propose a practical high-probability
Externí odkaz:
http://arxiv.org/abs/2411.01293
The covariance for clean data given a noisy observation is an important quantity in many conditional generation methods for diffusion models. Current methods require heavy test-time computation, altering the standard diffusion training process or den
Externí odkaz:
http://arxiv.org/abs/2410.11149
In turbulent flows, tracking the source of a passive scalar cue requires exploiting the limited information that can be gleaned from rare, stochastic encounters with the cue. When crafting a search policy, the most challenging and important decision
Externí odkaz:
http://arxiv.org/abs/2409.11343
Several generative models with elaborate training and sampling procedures have been proposed recently to accelerate structure-based drug design (SBDD); however, perplexingly, their empirical performance turns out to be suboptimal. We seek to better u
Externí odkaz:
http://arxiv.org/abs/2408.06050
Autor:
Darnet, Mathieu, Kim, Bitnarae, Vedrine, Simon, Deparis, Jacques, Bretaudeau, Francois, Gance, Julien, Vermeersch, Fabrice, Truffert, Catherine, Autio, Uula, Kamm, Jochen, Patzer, Cedric, Kalscheuer, Thomas, Heinonen, Suvi
Publikováno v:
EAGE NSG 2024, Sep 2024, Helsinki (FI), Finland
The transition towards carbon neutral transportation and energy sources increases the global demand for mineral raw materials while easy-to-find near-surface (\< 200 m) ore deposits are unlikely discovered in well-explored areas such as Europe. In or
Externí odkaz:
http://arxiv.org/abs/2407.11445
The problem of locating an odor source in turbulent flows is central to key applications such as environmental monitoring and disaster response. We address this challenge by designing an algorithm based on Bayesian inference, which uses odor measurem
Externí odkaz:
http://arxiv.org/abs/2407.08343
Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to those corruptions but may harm performance on clean images and other
Externí odkaz:
http://arxiv.org/abs/2406.16540
Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach of coupling data
Externí odkaz:
http://arxiv.org/abs/2406.01494
In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptimal compared to autoregressive generative models. This paper tackles the
Externí odkaz:
http://arxiv.org/abs/2405.17889
Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task. Diffusion models are a particularly promising modelling approach, enabling post-hoc conditioning and trading off
Externí odkaz:
http://arxiv.org/abs/2405.17656