Picture for Joe Benton

Joe Benton

Sabotage Evaluations for Frontier Models

Add code
Oct 28, 2024
Figure 1 for Sabotage Evaluations for Frontier Models
Figure 2 for Sabotage Evaluations for Frontier Models
Figure 3 for Sabotage Evaluations for Frontier Models
Figure 4 for Sabotage Evaluations for Frontier Models
Viaarxiv icon

When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?

Add code
Jul 21, 2024
Figure 1 for When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
Figure 2 for When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
Figure 3 for When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
Figure 4 for When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
Viaarxiv icon

Measuring Feature Sparsity in Language Models

Add code
Oct 13, 2023
Viaarxiv icon

Linear Convergence Bounds for Diffusion Models via Stochastic Localization

Add code
Aug 07, 2023
Viaarxiv icon

Error Bounds for Flow Matching Methods

Add code
May 26, 2023
Viaarxiv icon

From Denoising Diffusions to Denoising Markov Models

Add code
Nov 07, 2022
Viaarxiv icon

Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics

Add code
Oct 12, 2022
Figure 1 for Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
Figure 2 for Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
Figure 3 for Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
Figure 4 for Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
Viaarxiv icon

Polysemanticity and Capacity in Neural Networks

Add code
Oct 04, 2022
Figure 1 for Polysemanticity and Capacity in Neural Networks
Figure 2 for Polysemanticity and Capacity in Neural Networks
Figure 3 for Polysemanticity and Capacity in Neural Networks
Figure 4 for Polysemanticity and Capacity in Neural Networks
Viaarxiv icon

A Continuous Time Framework for Discrete Denoising Models

Add code
May 30, 2022
Figure 1 for A Continuous Time Framework for Discrete Denoising Models
Figure 2 for A Continuous Time Framework for Discrete Denoising Models
Figure 3 for A Continuous Time Framework for Discrete Denoising Models
Figure 4 for A Continuous Time Framework for Discrete Denoising Models
Viaarxiv icon