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. I collaborate closely with Professor Pavel Izmailov and Professor Yejin Choi.
My research focuses on improving the reasoning and planning capabilities of language models through reinforcement learning. I am interested in developing AI systems that can perform multi-step reasoning over complex problems, devise and execute plans, effectively use tools, and collaborate through communication and debate. Currently, I am working on efficient exploration strategies in RL, reinforcement learning with dense rewards for long-horizon tasks, and multi-agent systems with collaborative reasoning.
Some of my recent projects include SPARK (reference-free RL training with generative process reward models), X-Teaming (adaptive multi-agent jailbreaks and defenses), MOSAIC (social AI for content dissemination), Xolver (multi-agent reasoning with experience learning), and AI Debate (scalable oversight for factuality claims).
Recently, I interned with Amazon's AGI team, where I worked on generative process reward models for improving LLM reasoning through reinforcement learning. Previously, I interned at Apple's machine learning team, developing efficient multimodal LLMs for on-device deployment. At UCLA, I help organize the NLP Seminar Series.
Before joining UCLA, I worked at NYU 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
AI Debate paper accepted at NeurIPS 2025!
MOSAIC paper accepted at EMNLP 2025!
X-Teaming paper accepted at COLM 2025!
Xolver paper on multi-agent reasoning with holistic experience learning available as a preprint.
Excited to join Amazon AGI Team as Applied Scientist Intern!
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