Georg Wölflein — accepted AI-conference papers

2025

LLM Agents Making Agent Tools

Georg Wölflein, Dyke Ferber, Daniel Truhn, Ognjen Arandjelovic, Jakob Nikolas Kather

ACL 2025long

Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers, hindering the applicability of LLM agents in domains demandi…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

Tim Lenz, Peter Neidlinger, Marta Ligero, Georg Wölflein, Marko van Treeck, Jakob N. Kather

CVPR 2025poster

Representation learning of pathology whole-slide images (WSIs) has primarily relied on weak supervision with Multiple Instance Learning (MIL). This approach leads to slide representations highly tailored to a specific clinical task. Self-supervised learning (SSL) has been successfully applied to tra…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗