David W. Romero

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 30

Top Topics

General Purpose

Discrete Valued

Convolution Kernel

Top Venues

Publications

David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
Wavelet Networks: Scale-Translation Equivariant Learning From Raw Time-Series. Trans. Mach. Learn. Res. 2024 (2024)
Erik J. Bekkers, Sharvaree P. Vadgama, Rob Hesselink, Putri A. van der Linden, David W. Romero
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space. ICLR (2024)
Stefano Massaroli, Michael Poli, Daniel Y. Fu, Hermann Kumbong, Rom N. Parnichkun, Aman Timalsina, David W. Romero, Quinn McIntyre, Beidi Chen, Atri Rudra, Ce Zhang, Christopher Ré, Stefano Ermon, Yoshua Bengio
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions. CoRR (2023)
Erik J. Bekkers, Sharvaree P. Vadgama, Rob D. Hesselink, Putri A. van der Linden, David W. Romero
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space. CoRR (2023)
Alonso Urbano, David W. Romero
Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries. CoRR (2023)
Putri A. van der Linden, David W. Romero, Erik J. Bekkers
Learned Gridification for Efficient Point Cloud Processing. TAG-ML (2023)
David W. Romero, Neil Zeghidour
DNArch: Learning Convolutional Neural Architectures by Backpropagation. CoRR (2023)
David M. Knigge, David W. Romero, Albert Gu, Efstratios Gavves, Erik J. Bekkers, Jakub Mikolaj Tomczak, Mark Hoogendoorn, Jan-Jakob Sonke
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN. ICLR (2023)
Putri A. van der Linden, David W. Romero, Erik J. Bekkers
Learned Gridification for Efficient Point Cloud Processing. CoRR (2023)
David M. Knigge, David W. Romero, Albert Gu, Efstratios Gavves, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn, Jan-Jakob Sonke
Modelling Long Range Dependencies in N-D: From Task-Specific to a General Purpose CNN. CoRR (2023)
Stefano Massaroli, Michael Poli, Daniel Y. Fu, Hermann Kumbong, Rom N. Parnichkun, David W. Romero, Aman Timalsina, Quinn McIntyre, Beidi Chen, Atri Rudra, Ce Zhang, Christopher Ré, Stefano Ermon, Yoshua Bengio
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions. NeurIPS (2023)
David W. Romero, Suhas Lohit
Learning Partial Equivariances From Data. NeurIPS (2022)
David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub Mikolaj Tomczak, Mark Hoogendoorn
CKConv: Continuous Kernel Convolution For Sequential Data. ICLR (2022)
David W. Romero, Robert-Jan Bruintjes, Jakub Mikolaj Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan van Gemert
FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes. ICLR (2022)
David W. Romero, David M. Knigge, Albert Gu, Erik J. Bekkers, Efstratios Gavves, Jakub M. Tomczak, Mark Hoogendoorn
Towards a General Purpose CNN for Long Range Dependencies in ND. CoRR (2022)
Tycho F. A. van der Ouderaa, David W. Romero, Mark van der Wilk
Relaxing Equivariance Constraints with Non-stationary Continuous Filters. CoRR (2022)
Tycho F. A. van der Ouderaa, David W. Romero, Mark van der Wilk
Relaxing Equivariance Constraints with Non-stationary Continuous Filters. NeurIPS (2022)
David M. Knigge, David W. Romero, Erik J. Bekkers
Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups. ICML (2022)
David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
CKConv: Continuous Kernel Convolution For Sequential Data. CoRR (2021)
David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan C. van Gemert
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes. CoRR (2021)
David M. Knigge, David W. Romero, Erik J. Bekkers
Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups. CoRR (2021)
David W. Romero, Jean-Baptiste Cordonnier
Group Equivariant Stand-Alone Self-Attention For Vision. ICLR (2021)
David W. Romero, Suhas Lohit
Learning Equivariances and Partial Equivariances from Data. CoRR (2021)
David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
Attentive Group Equivariant Convolutional Networks. ICML (2020)
Alessandro Zonta, Ali El Hassouni, David W. Romero, Jakub M. Tomczak
Generative Fourier-Based Auto-encoders: Preliminary Results. LOD (2) (2020)
David W. Romero, Jean-Baptiste Cordonnier
Group Equivariant Stand-Alone Self-Attention For Vision. CoRR (2020)
David W. Romero, Mark Hoogendoorn
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in Data. ICLR (2020)
David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
Wavelet Networks: Scale Equivariant Learning From Raw Waveforms. CoRR (2020)
David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
Attentive Group Equivariant Convolutional Networks. CoRR (2020)
David W. Romero, Mark Hoogendoorn
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data. CoRR (2019)