I’m currently a Research Associate at University of Waterloo working with Prof. Elliot Creager. Before that, I was a research intern at Vector Institute working with Prof. Gautam Kamath. I received my MMath in Computer Science from the University of Waterloo and fortunate to be advised by Prof. Lukasz Golab. I have been collaborating closely with Prof. Mohammad Mohammadi Amiri. I recieved my bachelor degree in Computer Science at Sharif University of Technology. I was a scientific intern at Max Planck Institute for Software Systems, Germany where I had the great pleasure to work with Professor Laurent Bindschaedler.

📌 Research Interests

My main areas of interests include:

• AI Safety and Alignment
• Large Language Models
• Data Centric AI

🗞 News

• [05/2026] Our paper Back to the Basics: Revisiting the Median for Out-of-Distribution Detection from Unlabeled Data was accepted to Transactions on Machine Learning Research (TMLR) for publication!

• [05/2025] Successfully defended my Master’s degree at the David R. Cheriton School of Computer Science, University of Waterloo!

• [05/2025] Our paper DriftXpress: Faster Drifting Models via Projected RKHS Fields is now available on arXiv.

• [04/2025] Our paper Curated Synthetic Data Doesn’t Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences was accepted by ICML 26, South Korea for publication!

• [11/2025] Our paper The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation was accepted by AAAI 26, Singapore for publication!

• [10/2025] Our paper Back to the Basics: Revisiting the Median for Out-of-Distribution Detection from Unlabeled Data is now available on arXiv.

• [10/2025] Gave a talk “We Are Losing the War for Real Data, It Is Time to Mark the Originals” at SoLaR @ COLM 2025 (October 2025).

• [08/2025] Our paper The Alignment Game: The Inevitable Conflict of Values in Generative Models was accepted by Conference on Language Modeling (COLM) Workshop on Socially Responsible Language Modelling Research (SoLaR), Montreal, Canada, 2025.

• [07/2025] Our paper SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching was accepted by Conference on Language Modeling (COLM) Montreal, Canada, 2025 for publication! code

• [07/2025] Received the José Blakeley Scholarship in Data Systems ($10,000) from University of Waterloo.

• [06/2025] Our paper Embrace the diversity: Avoiding mode collapse with polarized curation in generative retraining was accepted by International Conference on Machine Learning (ICML) Workshop on DataWorld: Unifying data curation frameworks across domains, Vancouver, Canada, 2025.

• [06/2025] Our paper Fragile by Design: Formalizing Watermarking Tradeoffs via Paraphrasing was accepted by International Conference on Machine Learning (ICML) Workshop on Technical AI Governance, Vancouver, Canada, 2025.

• [01/2025] Started my Master’s at the Cheriton School of Computer Science, University of Waterloo!