Alert button
Picture for Alessandro Achille

Alessandro Achille

Alert button

Leveraging sparse and shared feature activations for disentangled representation learning

Apr 17, 2023
Marco Fumero, Florian Wenzel, Luca Zancato, Alessandro Achille, Emanuele Rodolà, Stefano Soatto, Bernhard Schölkopf, Francesco Locatello

Figure 1 for Leveraging sparse and shared feature activations for disentangled representation learning
Figure 2 for Leveraging sparse and shared feature activations for disentangled representation learning
Figure 3 for Leveraging sparse and shared feature activations for disentangled representation learning
Figure 4 for Leveraging sparse and shared feature activations for disentangled representation learning
Viaarxiv icon

AI Model Disgorgement: Methods and Choices

Apr 07, 2023
Alessandro Achille, Michael Kearns, Carson Klingenberg, Stefano Soatto

Figure 1 for AI Model Disgorgement: Methods and Choices
Viaarxiv icon

Train/Test-Time Adaptation with Retrieval

Mar 25, 2023
Luca Zancato, Alessandro Achille, Tian Yu Liu, Matthew Trager, Pramuditha Perera, Stefano Soatto

Figure 1 for Train/Test-Time Adaptation with Retrieval
Figure 2 for Train/Test-Time Adaptation with Retrieval
Figure 3 for Train/Test-Time Adaptation with Retrieval
Figure 4 for Train/Test-Time Adaptation with Retrieval
Viaarxiv icon

Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models

Mar 07, 2023
Yonatan Dukler, Alessandro Achille, Hao Yang, Varsha Vivek, Luca Zancato, Ben Bowman, Avinash Ravichandran, Charless Fowlkes, Ashwin Swaminathan, Stefano Soatto

Figure 1 for Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models
Figure 2 for Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models
Figure 3 for Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models
Figure 4 for Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models
Viaarxiv icon

Spacetime-Efficient Low-Depth Quantum State Preparation with Applications

Mar 03, 2023
Kaiwen Gui, Alexander M. Dalzell, Alessandro Achille, Martin Suchara, Frederic T. Chong

Figure 1 for Spacetime-Efficient Low-Depth Quantum State Preparation with Applications
Figure 2 for Spacetime-Efficient Low-Depth Quantum State Preparation with Applications
Figure 3 for Spacetime-Efficient Low-Depth Quantum State Preparation with Applications
Figure 4 for Spacetime-Efficient Low-Depth Quantum State Preparation with Applications
Viaarxiv icon

A Meta-Learning Approach to Predicting Performance and Data Requirements

Mar 02, 2023
Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto

Figure 1 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Figure 2 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Figure 3 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Figure 4 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Viaarxiv icon

Linear Spaces of Meanings: the Compositional Language of VLMs

Feb 28, 2023
Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille, Parminder Bhatia, Bing Xiang, Stefano Soatto

Figure 1 for Linear Spaces of Meanings: the Compositional Language of VLMs
Figure 2 for Linear Spaces of Meanings: the Compositional Language of VLMs
Figure 3 for Linear Spaces of Meanings: the Compositional Language of VLMs
Figure 4 for Linear Spaces of Meanings: the Compositional Language of VLMs
Viaarxiv icon

À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting

Feb 15, 2023
Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto

Figure 1 for À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Figure 2 for À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Figure 3 for À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Figure 4 for À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Viaarxiv icon

Integral Continual Learning Along the Tangent Vector Field of Tasks

Nov 23, 2022
Tian Yu Liu, Aditya Golatkar, Stefano Soatto, Alessandro Achille

Figure 1 for Integral Continual Learning Along the Tangent Vector Field of Tasks
Figure 2 for Integral Continual Learning Along the Tangent Vector Field of Tasks
Figure 3 for Integral Continual Learning Along the Tangent Vector Field of Tasks
Figure 4 for Integral Continual Learning Along the Tangent Vector Field of Tasks
Viaarxiv icon

Critical Learning Periods for Multisensory Integration in Deep Networks

Oct 06, 2022
Michael Kleinman, Alessandro Achille, Stefano Soatto

Figure 1 for Critical Learning Periods for Multisensory Integration in Deep Networks
Figure 2 for Critical Learning Periods for Multisensory Integration in Deep Networks
Figure 3 for Critical Learning Periods for Multisensory Integration in Deep Networks
Figure 4 for Critical Learning Periods for Multisensory Integration in Deep Networks
Viaarxiv icon