Alessandro Achille

26

Papers

30

Total Citations

Papers (26)

CPR: Retrieval Augmented Generation for Copyright Protection

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

Multi-Modal Hallucination Control by Visual Information Grounding

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

Mixed-Privacy Forgetting in Deep Networks

LQF: Linear Quadratic Fine-Tuning

Mixed Differential Privacy in Computer Vision

Task Adaptive Parameter Sharing for Multi-Task Learning

Train/Test-Time Adaptation With Retrieval

Critical Learning Periods for Multisensory Integration in Deep Networks

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

A Meta-Learning Approach to Predicting Performance and Data Requirements

Task2Vec: Task Embedding for Meta-Learning

LayoutTransformer: Layout Generation and Completion With Self-Attention

SAFE: Machine Unlearning With Shard Graphs

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

Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment

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

Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies

Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence

Predicting Training Time Without Training

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

On Leave-One-Out Conditional Mutual Information For Generalization

Leveraging sparse and shared feature activations for disentangled representation learning

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

Gacs-Korner Common Information Variational Autoencoder