collaborators

6 papers

q-bio.NC2026

Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience

Johannes Bertram, Luciano Dyballa, T. Anderson Keller +2

Decoding approaches are widely used in neuroscience and machine learning to compare stimulus representations across neural systems, such as different brain regions, organisms, and…

q-bio.NC2026

Inferring Active Neural Circuits Using Diffusion Scores

Savik Kinger, Johannes Bertram, Luciano Dyballa +2

In biological systems, neural circuits compute through directed, short-latency interactions whose effects unfold across multiple time scales and behavioral contexts. We address the…

cs.CR2026

NESSiE: The Necessary Safety Benchmark -- Identifying Errors that should not Exist

Johannes Bertram, Jonas Geiping

We introduce NESSiE, the NEceSsary SafEty benchmark for large language models (LLMs). With minimal test cases of information and access security, NESSiE reveals safety-relevant fai…

q-bio.NC2026

How 'Neural' is a Neural Foundation Model?

Johannes Bertram, Luciano Dyballa, Anderson Keller +2

Foundation models have shown remarkable success in fitting biological visual systems; however, their black-box nature inherently limits their utility for understanding brain functi…

q-bio.NC2025

Manifolds and Modules: How Function Develops in a Neural Foundation Model

Johannes Bertram, Luciano Dyballa, T. Anderson Keller +2

Foundation models have shown remarkable success in fitting biological visual systems; however, their black-box nature inherently limits their utility for understanding brain functi…

cs.HC2025

Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI

Elisa Nguyen, Johannes Bertram, Evgenii Kortukov +2

Explainable AI (XAI) aims to make AI systems more transparent, yet many practices emphasise mathematical rigour over practical user needs. We propose an alternative to this model-c…