September 2025: Received the Czech Senate Medal (a civilian honor).
August 2025: IJCAI-W paper 'Human Action CLIPs' won the best paper award.
Paper 'Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders' under review.
Paper 'Human Action CLIPs: Detecting AI-generated Human Motion' published at IJCAI-W 2025.
Paper 'The DeepSpeak Dataset' published on ArXiv.
Paper 'Nepotistically Trained Generative-AI Models Collapse' published at ICLR-W 2025.
Paper 'GenAI Confessions: Black-box Membership Inference for Generative Image Models' published at ICCV-W 2025.
Paper 'Synthetic Human Action Video Data Generation with Pose Transfer' published at CVPR-W 2025.
Research Experience
Conducting research at Stanford University and Google DeepMind, focusing on AI, computer vision, and media forensics.
Education
Student at Stanford University, advised by Prof. Hany Farid and Prof. Maneesh Agrawala.
Background
A student at Stanford University and a student researcher at Google DeepMind. Advised by Prof. Hany Farid and Prof. Maneesh Agrawala, working at the intersection of AI, computer vision, and media forensics. The goal is to build AI systems that are inherently trustworthy and interpretable.
Miscellany
Email: maty (at) stanford (dot) edu
Resume (coming soon)
Last updated: October 6, 2025
Created with love and loads of iced coffee in San Francisco, USA.