Alessandro Laio
7 papers · 2019–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Academic Marathon (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
NIPS (6)
ICLR (1)
Top co-authors
Keywords
representation learning
(5)
neural network
(3)
convolutional neural network
(2)
intrinsic dimensionality
(2)
object recognition
(1)
visual cortex
(1)
self-supervised learning
(1)
neural network optimization
(1)
neural network theory
(1)
semantic hierarchy
(1)
intrinsic dimension
(1)
probability density
(1)
hidden layer
(1)
semantic information
(1)
deep convolutional neural network
(1)
learning dynamics
(1)
benign overfitting
(1)
generalization performance
(1)
simplicity bia
(1)
deep convolutional network
(1)
Papers
Emergence of a High-Dimensional Abstraction Phase in Language Transformers
ICLR 2025
A distributional simplicity bias in the learning dynamics of transformers
NIPS 2024
The geometry of hidden representations of large transformer models
NIPS 2023
Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks
NIPS 2022
Redundant representations help generalization in wide neural networks
NIPS 2022
Hierarchical nucleation in deep neural networks
NIPS 2020
Intrinsic dimension of data representations in deep neural networks
NIPS 2019