Maty Bohacek

Stanford & Google DeepMind — San Francisco, CA

I am a student at Stanford University and student researcher at Google DeepMind. Advised by Prof. Hany Farid and Prof. Maneesh Agrawala, I work at the intersection of AI, computer vision, and media forensics. My goal is to build AI systems that are inherently trustworthy and interpretable.

News

(January 2025)

Discussed AI and disinformation at Unicef’s DCE workshop in Nairobi, Kenya.

(November 2024)

Honored to receive the Czech AI Personality Award (Osobnost.ai) as the Discovery of the Year.
Discussed my research on Hyde Park Civilization, a Czech TV show about science.
Delivered a guest lecture in Stanford’s DATASCI 194D.
Joined a panel at the Aspen Institute’s Annual Conference in Prague, Czechia.
See full archive in my journal here.

Upcoming

(February 2025)

I will deliver an invited talk at the WACV workshop on synthetic realities in Tucson, AZ.

(March 2025)

I will deliver an invited talk at the Hoover Institution.
I will join a panel discussion and a fireside chat at SXSW in Austin, TX.

(April 2025)

I will deliver a short invited talk at the workshop on data quality at ACM WWW in Sydney, Australia.
I will deliver a keynote for the UNYP URC conference.

Highlighted Publications

* Equal contribution. Not necessarily chronological.

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders

Bohacek M.*, Fel T.*, Agrawala M., Lubana E. Under Review.
Project Paper Code Weights — Method for identifying blindspots in T2I models: concepts that the model was trained on but can’t generate.

Human Action CLIPS: Detecting AI-generated Human Motion

Bohacek M. & Farid H. IJCAI-W 2025.
Paper Dataset — This paper proposes a method for distinguishing real and fake (T2V) video using multi-modal semantic embeddings, evaluated on DeepAction, a new dataset of real and AI-generated human motion.

DeepSpeak Dataset v1.0

Barrington S., Bohacek M., and Farid H. ArXiv, abs/2408.05366.
Paper Dataset — This paper introduces DeepSpeak, a large-scale dataset of real and deepfake footage designed to support research on detecting state-of-the-art face-swap and lip-sync deepfakes.

Lost in Translation: Lip-Sync Deepfake Detection from Audio-Video Mismatch

Bohacek M. & Farid H. CVPR-W 2024.
Paper — Method for detecting lip-sync deepfakes by comparing mismatches between audio transcription and automated lip-reading.

Nepotistically Trained Generative-AI Models Collapse

Bohacek M. & Farid H. ICLR-W 2025.
Paper — This paper demonstrates how some generative AI models, when retrained on their own outputs, produce distorted images and struggle to recover even after retraining on real data.

Dataset of News Articles with Provenance Metadata for Media Relevance Assessment

Peterka T. & Bohacek M. ACL-W 2025.
Project Paper Code Data — We introduce a new benchmark for assessing relevance of media in news articles through provenance.

Has an AI Model Been Trained on Your Images?

Bohacek M. & Farid H. Under Review.
Paper Dataset — This paper introduces a method to determine whether a generative AI model was trained on a specific image, helping to address concerns around fair use and copyright in generative AI.

Synthetic Human Action Video Data Generation with Pose Transfer

Knapp V. & Bohacek M. CVPR-W 2025.
Project Paper Code Data — We show that synthetic data of human motion improves performance of action classification and understanding.

Can Pose Transfer Models Generate Realistic Human Motion?

Knapp V. & Bohacek M. FG-W 2025.
Project Paper Code Data — We create a framework for evaluating pose transfer with human participant studies. We demonstrate it on SOTA methods, outlining productive directions for future research.

For a complete list of my academic publications, please refer to my Google Scholar profile.

Open-Source Resources

Contact & Misc.

Email: maty (at) stanford (dot) edu
Resume (coming soon)