Enric Boix-Adsera
8 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Cross-Pollinator (15) π Academic Marathon (5) π Renaissance Researcher (5) π Interdisciplinary Bridge
π
Conference Polyglot
(4)
πΊοΈ
Taxonomy Completionist
(20)
π§
Keyword Pioneer
π
Trend Setter
β
The Questioner
Conferences
NIPS (5)
EMNLP (1)
ICLR (1)
JMLR (1)
Top co-authors
Keywords
neural network
(4)
gradient descent
(2)
representation learning
(1)
learning theory
(1)
stochastic gradient descent
(1)
metric learning
(1)
hierarchical learning
(1)
optimal transport
(1)
prompt engineering
(1)
fourier analysis
(1)
deep learning
(1)
neural network optimization
(1)
maximum likelihood
(1)
experimental design
(1)
linear programming
(1)
hierarchical structure
(1)
polynomial time
(1)
deep neural network
(1)
language model
(1)
learning dynamics
(1)
Papers
Prompts have evil twins
EMNLP 2024
When can transformers reason with abstract symbols?
ICLR 2024
Transformers learn through gradual rank increase
NIPS 2023
GULP: a prediction-based metric between representations
NIPS 2022
On the non-universality of deep learning: quantifying the cost of symmetry
NIPS 2022
Wasserstein barycenters can be computed in polynomial time in fixed dimension
JMLR 2021
The staircase property: How hierarchical structure can guide deep learning
NIPS 2021
Sample Efficient Active Learning of Causal Trees
NIPS 2019