NEWS
A benchmark for trustworthy clinical AI
A new study published in Nature Communications shows that today's pathology foundation models can be influenced by the origin of a tissue sample. Researchers at BIFOLD and Aignostics developed PathoROB, a first-of-its-kind benchmark to measure and reduce this bias, shaping how the next generation of pathology AI is built.
Photo recap: LNDW 2026
On June 6, 2026, four members of the Berlin AI Square (BIFOLD, PTB, DFKI, and Fraunhofer HHI) joined forces at the Lange Nacht der Wissenschaften to showcase what the network achieves: an interactive LLM workshop and a well-attended Science Slam.
EVENTS
HIDA Lecture: Agentic AI - Safe Autonomous Agents
Toward the end of 2025, autonomous AI agents made significant leaps in capability. Smarter coding agents, a growing ecosystem of integrations exposed as skills and Model Context Protocol (MCP) servers, and projects like OpenClaw have demonstrated how these components can be combined into self-evolving AI systems.
Explanation-Aware Attacks and the Limits of using XAI
Modern (deep) learning methods used to lack understandable reasoning in their decision process, making crucial decisions less trustworthy. The research field of "Explainable AI" (XAI) has turned the tables, though, enabling precise relevance attribution of input features for otherwise opaque models.
*Data collected from 2020 onwards.
OPPORTUNITIES
BIFOLD welcomes job applications from interested parties year-round.
PUBLICATIONS
Gereon Dusella, Haralampos Gavriilidis, Volker Markl, Eleni Tzirita Zacharatou
Benchmarking Spatial Operations over Heterogeneous Data: The Case of Zonal Statistics
Yanqing Luo, Julius Hense, Niklas Prenißl, Andreas Mock, Klaus-Robert Müller, Thomas Schnake, Mina Jamshidi Idaji
Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
Marco Morik, Xiao Ruiting, Shinichi Nakajima, Stefan Haufe, Ismail Huseynov
Structure-Preserving Correction Learning for Sparse Bayesian Inference in Brain Source Imaging
GRADUATE SCHOOL
Based on a highly competitive application process, the BIFOLD Graduate School offers an innovative fast-track PhD Program for students holding a bachelor’s degree, as well as a PhD Program for students with a master’s degree.
INSTITUTIONAL PARTNERS
ASSOCIATED PARTNERS
