Salman Rahman

I am a second-year Ph.D. student fortunate to be co-advised by Professor Pavel Izmailov at NYU and Professor Saadia Gabriel at UCLA. I work closely with Professor Yejin Choi and Professor Nanyun Peng.

My research focuses on improving the reasoning and planning capabilities of language models and agents. I am also interested in developing training recipes and post-training methods that enable models to solve long-horizon tasks, problems that would take humans hours or more to complete.

Some of my recent projects include RLVR-Weak-Supervision (when and why LLMs learn to reason under weak supervision), CoDaS (AI co-data-scientist for digital biomarker discovery from wearables), SPARK (reference-free RL training with generative process reward models), Xolver (multi-agent reasoning with experience learning), and AI Debate (scalable oversight for factuality claims).

Currently, I am a student researcher at Google, working on AI for scientific discovery. Previously, I interned with Amazon's AGI team working on generative process reward models for improving LLM reasoning, and 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 related to scalable oversight and AI safety.

News

Mar, 2026

Passed my oral qualification exam and advanced to PhD candidacy!

Jan, 2026

Excited to join Google as Student Researcher!

Sep, 2025

AI Debate paper accepted at NeurIPS 2025!

Aug, 2025

MOSAIC paper accepted at EMNLP 2025!

Jul, 2025

X-Teaming paper accepted at COLM 2025!

Selected Publications

RLVR Weak Supervision

When Can LLMs Learn to Reason with Weak Supervision?

Salman Rahman, Jingyan Shen, Anna Mordvina, Hamid Palangi, Saadia Gabriel, Pavel Izmailov

TBD, 2026 PDF (Coming Soon)

CoDaS Framework

CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors

Yubin Kim, Salman Rahman, Samuel Schmidgall, Chunjong Park, A. Ali Heydari, Ahmed A. Metwally, Hong Yu, Xin Liu, Xuhai Xu, Yuzhe Yang, Maxwell A. Xu, Zhihan Zhang, Cynthia Breazeal, Tim Althoff, Petar Sirkovic, Ivor Rendulic, Annalisa Pawlosky, Nicolas Stroppa, Juraj Gottweis, Elahe Vedadi, Alan Karthikesalingam, Pushmeet Kohli, Vivek Natarajan, Mark Malhotra, Shwetak Patel, Hae Won Park, Hamid Palangi, Daniel McDuff

TBD, 2026 PDF (Coming Soon)

SPARK Framework

SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning

Salman Rahman, Sruthi Gorantla, Arpit Gupta, Swastik Roy, Nanyun Peng, Yang Liu

arXiv preprint, 2025 PDF

Xolver Framework

Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team

Md Tanzib Hosain, Salman Rahman, Md Kishor Morol, Md Rizwan Parvez

arXiv preprint, 2025 PROJECT PDF CODE

AI Debate Framework

AI Debate Aids Assessment of Controversial Claims

Salman Rahman, Sheriff Issaka, Ashima Suvarna, Genglin Liu, James Shiffer, Jaeyoung Lee, Md Rizwan Parvez, Hamid Palangi, Shi Feng, Nanyun Peng, Yejin Choi, Julian Michael, Liwei Jiang, Saadia Gabriel

NeurIPS, 2025 PDF CODE

X-Teaming Framework

𝕏-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

Salman Rahman*, Liwei Jiang*, James Shiffer*, Genglin Liu, Sheriff Issaka, Md Rizwan Parvez, Hamid Palangi, Kai-Wei Chang, Yejin Choi, Saadia Gabriel

COLM, 2025 PROJECT PDF CODE

Social Simulation Framework

MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations

Genglin Liu, Vivian Le, Salman Rahman, Elisa Kreiss, Marzyeh Ghassemi, Saadia Gabriel

EMNLP, 2025 PDF CODE

Image description

Understanding Disparities in Post Hoc Machine Learning Explanation

Vishwali Mhasawade, Salman Rahman, Zoe Haskell-Craig, Rumi Chunara

FAccT, 2024 PDF CODE

Healthcare AI Model

Generalization in Healthcare AI: Evaluation of a Clinical Large Language Model

Salman Rahman, Lavender Yao Jiang, Saadia Gabriel, Yindalon Aphinyanaphongs, Eric Karl Oermann, Rumi Chunara

arXiv preprint, 2024 PDF

PNAS Paper

Utilizing big data without domain knowledge impacts public health decision-making

Miao Zhang, Salman Rahman, Vishwali Mhasawade, Rumi Chunara

Proceedings of the National Academy of Sciences (PNAS), 2024 HTML

Teaching

Fall 2023

Guest Lecturer, Foundation(Large) Language Model
CS-GY 9223: Foundations of Data Science, Graduate, NYU