Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Feng, Leo"'
Autor:
Feng, Leo, Tung, Frederick, Hajimirsadeghi, Hossein, Ahmed, Mohamed Osama, Bengio, Yoshua, Mori, Greg
The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Transformers are computationally expensive at inference time, limiting thei
Externí odkaz:
http://arxiv.org/abs/2405.13956
Autor:
Korablyov, Maksym, Liu, Cheng-Hao, Jain, Moksh, van der Sloot, Almer M., Jolicoeur, Eric, Ruediger, Edward, Nica, Andrei Cristian, Bengio, Emmanuel, Lapchevskyi, Kostiantyn, St-Cyr, Daniel, Schuetz, Doris Alexandra, Butoi, Victor Ion, Rector-Brooks, Jarrid, Blackburn, Simon, Feng, Leo, Nekoei, Hadi, Gottipati, SaiKrishna, Vijayan, Priyesh, Gupta, Prateek, Rampášek, Ladislav, Avancha, Sasikanth, Bacon, Pierre-Luc, Hamilton, William L., Paige, Brooks, Misra, Sanchit, Jastrzebski, Stanislaw Kamil, Kaul, Bharat, Precup, Doina, Hernández-Lobato, José Miguel, Segler, Marwin, Bronstein, Michael, Marinier, Anne, Tyers, Mike, Bengio, Yoshua
Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exhibit a property of interest remains a significant challenge. We introduce LambdaZero, a generative active lear
Externí odkaz:
http://arxiv.org/abs/2405.01616
Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for each prediction, Cross Attention scans the full set of $\mathcal{O}(N)$ tokens. In practice, however, often onl
Externí odkaz:
http://arxiv.org/abs/2309.17388
Modern foundation model architectures rely on attention mechanisms to effectively capture context. However, these methods require linear or quadratic memory in terms of the number of inputs/datapoints, limiting their applicability in low-compute doma
Externí odkaz:
http://arxiv.org/abs/2306.12599
Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, however, leverage expensive attention mechanisms, limiting their applications, particularly in low-resource se
Externí odkaz:
http://arxiv.org/abs/2305.14567
Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong perfor
Externí odkaz:
http://arxiv.org/abs/2211.08458
The ability to accelerate the design of biological sequences can have a substantial impact on the progress of the medical field. The problem can be framed as a global optimization problem where the objective is an expensive black-box function such th
Externí odkaz:
http://arxiv.org/abs/2209.06259
We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset. Recent state-of-the-art selective methods come with architectural changes either via introduc
Externí odkaz:
http://arxiv.org/abs/2206.09034
Autor:
Deleu, Tristan, Kanaa, David, Feng, Leo, Kerg, Giancarlo, Bengio, Yoshua, Lajoie, Guillaume, Bacon, Pierre-Luc
Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specif
Externí odkaz:
http://arxiv.org/abs/2203.01443
Publikováno v:
In Powder Technology 15 March 2024 437