Deep Learning
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Neural Information Processing Systems http://nips.cc/
Trading robust representations for sample complexity through self-supervised visual experience
Andrea Tacchetti, Stephen Voinea, Georgios Evangelopoulos
Neural Information Processing Systems http://nips.cc/
Unsupervised learning of object structure and dynamics from videos
Matthias Minderer, Chen Sun, Ruben Villegas, Forrester Cole, Kevin P. Murphy, Honglak Lee
Neural Information Processing Systems http://nips.cc/
Representational Strengths and Limitations of Transformers
In recent years, transformer networks [V aswani et al., 2017] have been established as a fundamental neural architecture powering state-of-the-art results in many applications, including language
Representational Strengths and Limitations of Transformers
In recent years, transformer networks [V aswani et al., 2017] have been established as a fundamental neural architecture powering state-of-the-art results in many applications, including language
Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
Axel Brando, Jose A. Rodriguez, Jordi Vitria, Alberto Rubio Muรฑoz
Figure 2: On the bottom we see a representation oftheproposed regression model that captures all the componentsฯi of the mixture of Asymmetric Laplacian distributions (ALD)simultaneously.
Adaptive Cross-Modal Few-shot Learning
Chen Xing, Negar Rostamzadeh, Boris Oreshkin, Pedro O. O. Pinheiro
Neural Information Processing Systems http://nips.cc/
The Learnability of In-Context Learning
Our theoretical analysis reveals that in this setting, in-context learning is more about identifying the task than about learning it, a result which is in line with a series of recent empirical findings.