Zobrazeno 1 - 10
of 576
pro vyhledávání: '"P. Seitzer"'
Autor:
Didolkar, Aniket, Zadaianchuk, Andrii, Goyal, Anirudh, Mozer, Mike, Bengio, Yoshua, Martius, Georg, Seitzer, Maximilian
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to real-world scenes b
Externí odkaz:
http://arxiv.org/abs/2408.09162
No progenitor of a Type Ia supernova is known, but in old population early-type galaxies, one may find SN Ia associated with globular clusters, yielding a population age and metallicity. It also provides insight into the formation path and the SN enh
Externí odkaz:
http://arxiv.org/abs/2405.09701
Autor:
Seitzer, Maximilian, van Steenkiste, Sjoerd, Kipf, Thomas, Greff, Klaus, Sajjadi, Mehdi S. M.
Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene Transform
Externí odkaz:
http://arxiv.org/abs/2310.06020
Autor:
Katherine Labbé, Lauren LeBon, Bryan King, Ngoc Vu, Emily H. Stoops, Nina Ly, Austin E. Y. T. Lefebvre, Phillip Seitzer, Swathi Krishnan, Jin-Mi Heo, Bryson Bennett, Carmela Sidrauski
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-21 (2024)
Abstract The integrated stress response (ISR) enables cells to cope with a variety of insults, but its specific contribution to downstream cellular outputs remains unclear. Using a synthetic tool, we selectively activate the ISR without co-activation
Externí odkaz:
https://doaj.org/article/27e86f13e45248efb23da08ad179a50a
Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted domains. Recen
Externí odkaz:
http://arxiv.org/abs/2306.04829
Autor:
Ngoc Vu, Tobias M. Maile, Sudha Gollapudi, Aleksandr Gaun, Phillip Seitzer, Jonathon J. O’Brien, Sean R. Hackett, Jose Zavala-Solorio, Fiona E. McAllister, Ganesh Kolumam, Rob Keyser, Bryson D. Bennett
Publikováno v:
Journal of Lipid Research, Vol 65, Iss 9, Pp 100607- (2024)
Blood plasma is one of the most commonly analyzed and easily accessible biological samples. Here, we describe an automated liquid-liquid extraction platform that generates accurate, precise, and reproducible samples for metabolomic, lipidomic, and pr
Externí odkaz:
https://doaj.org/article/4c2c7606b1f34ce2a12d36d49f908b45
Autor:
Seitzer, Maximilian, Horn, Max, Zadaianchuk, Andrii, Zietlow, Dominik, Xiao, Tianjun, Simon-Gabriel, Carl-Johann, He, Tong, Zhang, Zheng, Schölkopf, Bernhard, Brox, Thomas, Locatello, Francesco
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research.
Externí odkaz:
http://arxiv.org/abs/2209.14860
Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by maximizing the
Externí odkaz:
http://arxiv.org/abs/2203.09168
Many reinforcement learning (RL) environments consist of independent entities that interact sparsely. In such environments, RL agents have only limited influence over other entities in any particular situation. Our idea in this work is that learning
Externí odkaz:
http://arxiv.org/abs/2106.03443
Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge
Externí odkaz:
http://arxiv.org/abs/2011.14381