Roman Lutz

romanlutz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 2 months ago

Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness

Paper • 2510.01670 • Published Oct 2, 2025 • 6

authored 2 papers 11 months ago

PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System

Paper • 2410.02828 • Published Oct 1, 2024 • 1

Lessons From Red Teaming 100 Generative AI Products

Paper • 2501.07238 • Published Jan 13, 2025

authored a paper over 1 year ago

Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle

Paper • 2407.13833 • Published Jul 18, 2024 • 12

authored a paper almost 2 years ago

Fairlearn: Assessing and Improving Fairness of AI Systems

Paper • 2303.16626 • Published Mar 29, 2023

authored a paper about 2 years ago

A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications

Paper • 2310.17750 • Published Oct 26, 2023 • 9