Benton, Joe

12 publications

ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristobal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez

TMLR 2025 Inverse Scaling in Test-Time Compute Aryo Pradipta Gema, Alexander Hägele, Runjin Chen, Andy Arditi, Jacob Goldman-Wetzler, Kit Fraser-Taliente, Henry Sleight, Linda Petrini, Julian Michael, Beatrice Alex, Pasquale Minervini, Yanda Chen, Joe Benton, Ethan Perez

TMLR 2024 Error Bounds for Flow Matching Methods Joe Benton, George Deligiannidis, Arnaud Doucet

NeurIPSW 2024 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Zane Durante, Cristobal Eyzaguirre, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez

NeurIPSW 2024 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Zane Durante, Cristobal Eyzaguirre, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez

NeurIPS 2024 Many-Shot Jailbreaking Cem Anil, Esin Durmus, Nina Panickssery, Mrinank Sharma, Joe Benton, Sandipan Kundu, Joshua Batson, Meg Tong, Jesse Mu, Daniel Ford, Fracesco Mosconi, Rajashree Agrawal, Rylan Schaeffer, Naomi Bashkansky, Samuel Svenningsen, Mike Lambert, Ansh Radhakrishnan, Carson Denison, Evan J Hubinger, Yuntao Bai, Trenton Bricken, Timothy Maxwell, Nicholas Schiefer, James Sully, Alex Tamkin, Tamera Lanhan, Karina Nguyen, Tomasz Korbak, Jared Kaplan, Deep Ganguli, Samuel R. Bowman, Ethan Perez, Roger Baker Grosse, David Duvenaud

ICLR 2024 Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization Joe Benton, Valentin De Bortoli, Arnaud Doucet, George Deligiannidis

NeurIPSW 2024 When Do Universal Image Jailbreaks Transfer Between Vision-Language Models? Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristobal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez

NeurIPSW 2024 When Do Universal Image Jailbreaks Transfer Between Vision-Language Models? Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristobal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, Tony Tong Wang, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez

JMLR 2023 Alpha-Divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics Kamélia Daudel, Joe Benton, Yuyang Shi, Arnaud Doucet

NeurIPSW 2023 Measuring Feature Sparsity in Language Models Mingyang Deng, Lucas Tao, Joe Benton

NeurIPS 2022 A Continuous Time Framework for Discrete Denoising Models Andrew Campbell, Joe Benton, Valentin De Bortoli, Thomas Rainforth, George Deligiannidis, Arnaud Doucet