"Any sufficiently advanced technology is indistinguishable from magic."

Arthur C. Clarke, Profiles of the Future

I'm actively conducting research on AI safety and alignment, focusing on making AI systems more transparent and controllable.

Can Reasoning Models Obfuscate Reasoning?

NeurIPS FoRLM workshop

Vulnerability in Trusted Monitoring and Mitigations

June 07, 2025

Towards Efficient Feature-Splitting

August 31, 2024

Understanding High Dimensional Tensor Multiplication

July 08, 2024