Picture for Tuomas Oikarinen

Tuomas Oikarinen

Crafting Large Language Models for Enhanced Interpretability

Add code
Jul 05, 2024
Viaarxiv icon

Linear Explanations for Individual Neurons

Add code
May 10, 2024
Viaarxiv icon

Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models

Add code
Mar 20, 2024
Figure 1 for Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models
Figure 2 for Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models
Figure 3 for Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models
Figure 4 for Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models
Viaarxiv icon

Corrupting Neuron Explanations of Deep Visual Features

Add code
Oct 25, 2023
Viaarxiv icon

The Importance of Prompt Tuning for Automated Neuron Explanations

Add code
Oct 11, 2023
Viaarxiv icon

Concept-Monitor: Understanding DNN training through individual neurons

Add code
Apr 26, 2023
Viaarxiv icon

Label-Free Concept Bottleneck Models

Add code
Apr 12, 2023
Viaarxiv icon

CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks

Add code
Apr 23, 2022
Figure 1 for CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Figure 2 for CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Figure 3 for CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Figure 4 for CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Viaarxiv icon

Robust Deep Reinforcement Learning through Adversarial Loss

Add code
Aug 05, 2020
Figure 1 for Robust Deep Reinforcement Learning through Adversarial Loss
Figure 2 for Robust Deep Reinforcement Learning through Adversarial Loss
Figure 3 for Robust Deep Reinforcement Learning through Adversarial Loss
Figure 4 for Robust Deep Reinforcement Learning through Adversarial Loss
Viaarxiv icon