Alessandro Achille

papers

1,892

total citations

papers (23)

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

CVPR 2020arXiv

695

citations

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations

ECCV 2020arXiv

231

citations

Leveraging sparse and shared feature activations for disentangled representation learning

NEURIPS 2023arXiv

citations

LQF: Linear Quadratic Fine-Tuning

CVPR 2021arXiv

citations

SAFE: Machine Unlearning With Shard Graphs

ICCV 2023arXiv

citations

Predicting Training Time Without Training

NEURIPS 2020arXiv

citations

CPR: Retrieval Augmented Generation for Copyright Protection

CVPR 2024arXiv

citations

Gacs-Korner Common Information Variational Autoencoder

NEURIPS 2023arXiv

citations

A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting

CVPR 2023arXiv

citations

Critical Learning Periods for Multisensory Integration in Deep Networks

CVPR 2023arXiv

citations

Train/Test-Time Adaptation With Retrieval

CVPR 2023arXiv

citations

On Leave-One-Out Conditional Mutual Information For Generalization

NEURIPS 2022arXiv

citations

A Meta-Learning Approach to Predicting Performance and Data Requirements

CVPR 2023arXiv

citations

Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding

CVPR 2024arXiv

citations

Your representations are in the network: composable and parallel adaptation for large scale models

NEURIPS 2023arXiv

citations

On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning

NEURIPS 2021

citations

Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment

ECCV 2020

citations

Alessandro Achille

papers (23)

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations

Mixed-Privacy Forgetting in Deep Networks

LayoutTransformer: Layout Generation and Completion With Self-Attention

Multi-Modal Hallucination Control by Visual Information Grounding

Task Adaptive Parameter Sharing for Multi-Task Learning

Mixed Differential Privacy in Computer Vision

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models

Leveraging sparse and shared feature activations for disentangled representation learning

LQF: Linear Quadratic Fine-Tuning

SAFE: Machine Unlearning With Shard Graphs

Predicting Training Time Without Training

CPR: Retrieval Augmented Generation for Copyright Protection

Gacs-Korner Common Information Variational Autoencoder

A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting

Critical Learning Periods for Multisensory Integration in Deep Networks

Train/Test-Time Adaptation With Retrieval

On Leave-One-Out Conditional Mutual Information For Generalization

A Meta-Learning Approach to Predicting Performance and Data Requirements

Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding

Your representations are in the network: composable and parallel adaptation for large scale models

On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning

Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment

papers (23)

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations

Mixed-Privacy Forgetting in Deep Networks

LayoutTransformer: Layout Generation and Completion With Self-Attention

Multi-Modal Hallucination Control by Visual Information Grounding

Task Adaptive Parameter Sharing for Multi-Task Learning

Mixed Differential Privacy in Computer Vision

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models

Leveraging sparse and shared feature activations for disentangled representation learning

LQF: Linear Quadratic Fine-Tuning

SAFE: Machine Unlearning With Shard Graphs

Predicting Training Time Without Training

CPR: Retrieval Augmented Generation for Copyright Protection

Gacs-Korner Common Information Variational Autoencoder

A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting

Critical Learning Periods for Multisensory Integration in Deep Networks

Train/Test-Time Adaptation With Retrieval

On Leave-One-Out Conditional Mutual Information For Generalization

A Meta-Learning Approach to Predicting Performance and Data Requirements

Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding

Your representations are in the network: composable and parallel adaptation for large scale models

On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning

Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment