Mary-Anne Hartley — accepted AI-conference papers

2025

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

Mucong Ding, Bang An, Tahseen Rabbani, Chenghao Deng, Anirudh Satheesh, Souradip Chakraborty +13

NeurIPS 2025poster

AI-generated images have become pervasive, raising critical concerns around content authenticity, intellectual property, and the spread of misinformation. Invisible watermarks offer a promising solution for identifying AI-generated images, preserving content provenance without degrading visual quali…

Cited by 0 Source ↗Scholar ↗

2023

MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks

Vinitra Swamy, Malika Satayeva, Jibril Frej, Thierry Bossy, Thijs Vogels, Martin Jaggi +2

NeurIPS 2023poster

Predicting multiple real-world tasks in a single model often requires a particularly diverse feature space. Multimodal (MM) models aim to extract the synergistic predictive potential of multiple data types to create a shared feature space with aligned semantic meaning across inputs of drastically va…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗