Roman Lutz

Roman Lutz on Hugging Face Daily Papers: 3 papers, 0 in the top 3 of their day, 28 upvotes.

1. Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness 6 upvotes, #31 of 2025-10-03
2. Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle 8 upvotes, #10 of 2024-07-22
3. A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications 8 upvotes, #6 of 2023-10-30

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.