Tom Blanchard — accepted AI-conference papers

2026

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images

Aditya Kumar, Tom Blanchard, Adam Dziedzic, Franziska Boenisch

AAAI 2026technical

State-of-the-art Diffusion Models (DMs) produce highly realistic images. While prior work has successfully mitigated Not Safe For Work (NSFW) content in the visual domain, we identify a novel threat: the generation of NSFW text embedded within images. This includes offensive language, such as insult

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives

Vincent Hanke, Tom Blanchard, Franziska Boenisch, Iyiola Emmanuel Olatunji, Michael Backes, Adam Dziedzic

NeurIPS 2024poster

While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly *private* data. Recently, various new methods have been proposed to adapt clos…

Cited by 2 Source ↗PDF ↗Scholar ↗