Salman Rahman
Ph.D. Student in AI/NLP • UCLA

I am a Computer Science Ph.D. student at the University of California, Los Angeles, working under the supervision of Professor Saadia Gabriel. My research focuses on developing reliable multi-agent AI systems equipped with multi-step reasoning over complex problems, devise and execute plans, effectively use tools, and collaborate through communication and debate. In this area, I collaborate with Professor Yejin Choi and Pavel Izmailov.
My current research projects include X-Teaming, a framework for multi-turn jailbreaks and defenses with adaptive multi-agents; MOSAIC, modeling social AI for content dissemination in multi-agent simulations; Xolver, multi-agent reasoning with holistic experience learning; and AI Debate, using debate for assessment of controversial claims and scalable oversight.
I will be interning with Amazon's AGI team in Summer 2025. Previously, I interned at Apple's machine learning team in Summer 2024, where I worked on building, training, and evaluating efficient small-scale state-of-the-art multimodal LLMs for specialized computer vision tasks, designed for on-device deployment. At UCLA, I also help organize the UCLA NLP Seminar Series - stay tuned!
At NYU, I worked on projects including Clinical LLM generalization, machine learning explanation disparity, and big data in healthcare. During my undergraduate and master's studies, I focused on computational sustainability, exploring how AI systems can address pressing societal and environmental challenges of the 21st century. Explore my publications on computational sustainability here.
News
Xolver paper on multi-agent reasoning with holistic experience learning available as a preprint.
Excited to join Amazon AGI Team as Applied Scientist Intern!
AI Debate paper on assessment of controversial claims - checkout preprint.
X-Teaming paper on multi-turn jailbreaking with adaptive multi-agent systems available as a preprint.
Our MOSAIC paper on simulating social media using LLM agents is now available at preprint.
New paper accepted in Proceedings of the National Academy of Sciences (PNAS) on big data in healthcare.
Excited to join Apple's machine learning team as an intern!
One paper on machine learning explanation disparity is accepted to ACM FAccT 2024.
Selected Publications




Generalization in Healthcare AI: Evaluation of a Clinical Large Language Model
arXiv preprint, 2024 PDF

Utilizing big data without domain knowledge impacts public health decision-making
Proceedings of the National Academy of Sciences (PNAS), 2024 HTML
Teaching
Guest Lecturer, Foundation(Large) Language Model
CS-GY 9223: Foundations of Data Science, Graduate, NYU