Alert button
Picture for Maximilian Mozes

Maximilian Mozes

Alert button

Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge

Add code
Bookmark button
Alert button
Feb 29, 2024
Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu

Viaarxiv icon

Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities

Add code
Bookmark button
Alert button
Aug 24, 2023
Maximilian Mozes, Xuanli He, Bennett Kleinberg, Lewis D. Griffin

Figure 1 for Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Figure 2 for Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Figure 3 for Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Figure 4 for Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
Viaarxiv icon

Challenges and Applications of Large Language Models

Add code
Bookmark button
Alert button
Jul 19, 2023
Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, Robert McHardy

Viaarxiv icon

Susceptibility to Influence of Large Language Models

Add code
Bookmark button
Alert button
Mar 10, 2023
Lewis D Griffin, Bennett Kleinberg, Maximilian Mozes, Kimberly T Mai, Maria Vau, Matthew Caldwell, Augustine Marvor-Parker

Figure 1 for Susceptibility to Influence of Large Language Models
Figure 2 for Susceptibility to Influence of Large Language Models
Figure 3 for Susceptibility to Influence of Large Language Models
Figure 4 for Susceptibility to Influence of Large Language Models
Viaarxiv icon

Towards Agile Text Classifiers for Everyone

Add code
Bookmark button
Alert button
Feb 13, 2023
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon

Figure 1 for Towards Agile Text Classifiers for Everyone
Figure 2 for Towards Agile Text Classifiers for Everyone
Figure 3 for Towards Agile Text Classifiers for Everyone
Figure 4 for Towards Agile Text Classifiers for Everyone
Viaarxiv icon

Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning

Add code
Bookmark button
Alert button
Feb 13, 2023
Maximilian Mozes, Tolga Bolukbasi, Ann Yuan, Frederick Liu, Nithum Thain, Lucas Dixon

Figure 1 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Figure 2 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Figure 3 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Figure 4 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Viaarxiv icon

Textwash -- automated open-source text anonymisation

Add code
Bookmark button
Alert button
Aug 27, 2022
Bennett Kleinberg, Toby Davies, Maximilian Mozes

Figure 1 for Textwash -- automated open-source text anonymisation
Figure 2 for Textwash -- automated open-source text anonymisation
Figure 3 for Textwash -- automated open-source text anonymisation
Figure 4 for Textwash -- automated open-source text anonymisation
Viaarxiv icon

Scene Graph Generation for Better Image Captioning?

Add code
Bookmark button
Alert button
Sep 23, 2021
Maximilian Mozes, Martin Schmitt, Vladimir Golkov, Hinrich Schütze, Daniel Cremers

Figure 1 for Scene Graph Generation for Better Image Captioning?
Figure 2 for Scene Graph Generation for Better Image Captioning?
Figure 3 for Scene Graph Generation for Better Image Captioning?
Figure 4 for Scene Graph Generation for Better Image Captioning?
Viaarxiv icon

Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification

Add code
Bookmark button
Alert button
Sep 09, 2021
Maximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin

Figure 1 for Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Figure 2 for Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Figure 3 for Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Figure 4 for Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
Viaarxiv icon

Worry, coping and resignation -- A repeated-measures study on emotional responses after a year in the pandemic

Add code
Bookmark button
Alert button
Jul 07, 2021
Maximilian Mozes, Isabelle van der Vegt, Bennett Kleinberg

Figure 1 for Worry, coping and resignation -- A repeated-measures study on emotional responses after a year in the pandemic
Figure 2 for Worry, coping and resignation -- A repeated-measures study on emotional responses after a year in the pandemic
Figure 3 for Worry, coping and resignation -- A repeated-measures study on emotional responses after a year in the pandemic
Figure 4 for Worry, coping and resignation -- A repeated-measures study on emotional responses after a year in the pandemic
Viaarxiv icon