Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Scimeca, Luca"'
Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detection of OOD samples via Bayesian principles. An exis
Externí odkaz:
http://arxiv.org/abs/2409.16797
Autor:
Venkatraman, Siddarth, Jain, Moksh, Scimeca, Luca, Kim, Minsu, Sendera, Marcin, Hasan, Mohsin, Rowe, Luke, Mittal, Sarthak, Lemos, Pablo, Bengio, Emmanuel, Adam, Alexandre, Rector-Brooks, Jarrid, Bengio, Yoshua, Berseth, Glen, Malkin, Nikolay
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of
Externí odkaz:
http://arxiv.org/abs/2405.20971
Autor:
Sendera, Marcin, Kim, Minsu, Mittal, Sarthak, Lemos, Pablo, Scimeca, Luca, Rector-Brooks, Jarrid, Adam, Alexandre, Bengio, Yoshua, Malkin, Nikolay
We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and o
Externí odkaz:
http://arxiv.org/abs/2402.05098
Autor:
Scimeca, Luca, Rubinstein, Alexander, Teney, Damien, Oh, Seong Joon, Nicolicioiu, Armand Mihai, Bengio, Yoshua
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones. In this work, we pr
Externí odkaz:
http://arxiv.org/abs/2311.16176
Autor:
Scimeca, Luca, Rubinstein, Alexander, Nicolicioiu, Armand Mihai, Teney, Damien, Bengio, Yoshua
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones. In this work, we propose an
Externí odkaz:
http://arxiv.org/abs/2310.02230
Deep neural networks (DNNs) often rely on easy-to-learn discriminatory features, or cues, that are not necessarily essential to the problem at hand. For example, ducks in an image may be recognized based on their typical background scenery, such as l
Externí odkaz:
http://arxiv.org/abs/2110.03095
Autor:
Poli, Michael, Massaroli, Stefano, Scimeca, Luca, Oh, Seong Joon, Chun, Sanghyuk, Yamashita, Atsushi, Asama, Hajime, Park, Jinkyoo, Garg, Animesh
Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs), common across engineering domains, provide a formalism for dynamica
Externí odkaz:
http://arxiv.org/abs/2106.04165
Autor:
Suh, Jooyeon, Kim, Hyeonkyeong, Min, Jiyun, Yeon, Hyun Ju, Hemberg, Martin, Scimeca, Luca, Wu, Ming-Ru, Kang, Hyun Guy, Kim, Yi-Jun, Kim, Jin-Hong
Publikováno v:
In Cell Reports Medicine 16 January 2024 5(1)
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Zhang, Lingxiao, Zhu, Chaojie, Zhao, Jing, Scimeca, Luca, Dong, Mingdong, Liu, Ruitian, Jia, Yingbo, Xu, Zhi Ping
Publikováno v:
Advanced Functional Materials; May2024, Vol. 34 Issue 18, p1-26, 26p