David W. Romero
9 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Academic Marathon (5) π Conference Polyglot (3) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π₯
Unstoppable
(6)
Conferences
ICLR (6)
NIPS (2)
CVPR (1)
Top co-authors
Keywords
symmetry constraint
(2)
image classification
(1)
feature learning
(1)
image generation
(1)
computer vision
(1)
hierarchical modeling
(1)
geometric deep learning
(1)
parameter efficient
(1)
weight sharing
(1)
autoregressive model
(1)
convolutional neural network
(1)
masked prediction
(1)
equivariant learning
(1)
auto-regressive model
(1)
inference speed
(1)
visual autoregressive
(1)
translation equivariance
(1)
hierarchical generation
(1)
gradient-based learning
(1)
autoregressive image generation
(1)
Papers
HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
CVPR 2025
Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
ICLR 2024
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN
ICLR 2023
FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes
ICLR 2022
Relaxing Equivariance Constraints with Non-stationary Continuous Filters
NIPS 2022
Learning Partial Equivariances From Data
NIPS 2022
CKConv: Continuous Kernel Convolution For Sequential Data
ICLR 2022
Group Equivariant Stand-Alone Self-Attention For Vision
ICLR 2021
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in Data
ICLR 2020