Eugene Belilovsky

Affiliations

Mila

papers

358

total citations

papers (15)

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

ECCV 2024arXiv

106

citations

Probing Representation Forgetting in Supervised and Unsupervised Continual Learning

CVPR 2022arXiv

citations

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

ICML 2024arXiv

citations

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

AAAI 2024arXiv

citations

Simulated Annealing in Early Layers Leads to Better Generalization

CVPR 2023arXiv

citations

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

NEURIPS 2023arXiv

citations

AdaFisher: Adaptive Second Order Optimization via Fisher Information

ICLR 2025arXiv

citations

Accelerating Training with Neuron Interaction and Nowcasting Networks

ICLR 2025arXiv

citations

PETRA: Parallel End-to-end Training with Reversible Architectures

ICLR 2025arXiv

citations

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

NEURIPS 2025arXiv

citations

Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning

CVPR 2022

citations

Eugene Belilovsky

Affiliations

papers (15)

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

Probing Representation Forgetting in Supervised and Unsupervised Continual Learning

Generative Compositional Augmentations for Scene Graph Prediction

Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors

Parametric Scattering Networks

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

Simulated Annealing in Early Layers Leads to Better Generalization

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

AdaFisher: Adaptive Second Order Optimization via Fisher Information

Accelerating Training with Neuron Interaction and Nowcasting Networks

PETRA: Parallel End-to-end Training with Reversible Architectures

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning

papers (15)

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

Probing Representation Forgetting in Supervised and Unsupervised Continual Learning

Generative Compositional Augmentations for Scene Graph Prediction

Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors

Parametric Scattering Networks

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

Simulated Annealing in Early Layers Leads to Better Generalization

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

AdaFisher: Adaptive Second Order Optimization via Fisher Information

Accelerating Training with Neuron Interaction and Nowcasting Networks

PETRA: Parallel End-to-end Training with Reversible Architectures

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning