DCPO-T2I

AI & ML interests

Diffusion models, Preference Optimization

Recent Activity

sahsaeedi  authored a paper 7 days ago

UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization

sahsaeedi  authored a paper 7 days ago

Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization

sahsaeedi  authored a paper 7 days ago

When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers

View all activity

Team members 3