Hi, I’m Rasta

I’m currently a fourth-year PhD student in Computer Science at the Jeong Lab and the REAL AI Initiative at the University of California, Santa Barbara. My research interests lie at the intersection of Fair Machine Learning, with a focus on Generative AI, particularly Large Language Models and the application of AI for Science and Healthcare.

Currently, I’m focusing on confidence-calibrated reinforcement fine-tuning of language models for healthcare predictions, aiming to improve both reliability and trustworthiness. Previously, I worked on fair data imputation, where I used adversarial learning to address inequities in missing data imputation. This research also established theoretical connections between upstream imputation fairness and downstream predictive fairness.

Prior to my PhD, I obtained my BS in Computer Engineering from University of Tehran, Iran. While there, I worked on detecting hate speech in cross-lingual context in twitter posts using graph neural networks.

Please feel free to reach out if our work or interests align 😃

📣 News

• [Sep 2025]: Instructed our first iteration of REAL AI Bootcamp in collaboration with UCSB’s School of Scientific Thought.
• [Aug 2025]: Completed my candidacy exam and Master’s project presentation 🎉 Find the link to the presentation here.
• [July 2025]: Our paper FAIM: Fair Imputation with Adversarial Training for Mitigating Bias in Missing Data was accepted to the ICML 2025 Workshop on DataWorld: Unifying Data Curation Frameworks Across Domains.
• [June 2025]: Presented Gone With the Bits: Benchmarking Bias in Facial Phenotype Degradation Under Low-Rate Neural Compression (poster) at the IEEE International Symposium on Information Theory (ISIT) Workshop on Compression.
• [June 2025]: Our paper Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images was accepted to The ACM Conference on Fairness, Accountability, and Transparency (FAccT).
• [Apr 2025]: Our paper Learning to Lie: Reinforcement Learning Attacks Damage Human-AI Teams and Teams of LLMs was accepted as a spotlight presentation at the ICLR 2025 Workshop on Human-AI Coevolution (HAIC).
• [Jan 2025]: Gave a guest lecture at Bren School of Environmental Science & Management on Ethics of Machine Learning.
• [July 2024]: Our paper Gone With the Bits: Benchmarking Bias in Facial Phenotype Degradation Under Low-Rate Neural Compression was accepted to ICML 2024 Next Generation of AI Safety Workshop
• [June 2024]: Joined Jeong Lab at UC Santa Barbara
• [Aug 2023]: Attended my first conference SIGKDD 2023 as a student volunteer and proxy presenter
• [June 2023]: Received Computer Science Department Summer Fellowship Award
• [September 2022]: Started my PhD in computer science at UC Santa Barbara
• [June 2022]: Completed my BSc in Computer Engineering at the University of Tehran, graduating in the top 15% of my class