Luca M. Schulze Buschoff

luca.schulze-buschoff@helmholtz-munich.de
Google Scholar

I am a third year PhD student in cognitive science and machine learning under the supervision of Dr. Eric Schulz in the Institute for Human-Centered AI at Helmholtz AI, Munich Germany.

News

May 2026Our paper 'Can vision language models learn intuitive physics from interaction' was accepted to ICML'26.

April 2026I was named one of the top 200 reviewers for ICLR'26 (~1%).

April 2026I gave a talk in the CogToolsLab at Stanford.

April 2026I gave a talk in the Enigma project at Stanford.

March 2026I gave a talk in the Causality in Cognition lab at Stanford.

February 2026I'm visiting Tobias Gerstenberg's lab in Stanford until May.

Publications

Accepted at ICML 2026

Can vision language models learn intuitive physics from interaction?

L. M. Schulze Buschoff, K. Voudouris, C. Demircan, E. Schulz

Paper

Nature 2025

A foundation model to predict and capture human cognition

M. Binz, ..., L. M. Schulze Buschoff, ..., E. Schulz

Paper

ICML 2025

Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models

L. M. Schulze Buschoff*, K. Voudouris*, E. Akata, M. Bethge, J. B. Tenenbaum, E. Schulz

Paper

Nature Machine Intelligence 2025

Visual cognition in multimodal large language models

L. M. Schulze Buschoff*, E. Akata*, M. Bethge, E. Schulz

Paper

ICLR 2025

metabench -- A Sparse Benchmark to Measure General Ability in Large Language Models

A. Kipnis, K. Voudouris, L. M. Schulze Buschoff, E. Schulz

Paper

Preprint 2024

Next state prediction gives rise to entangled, yet compositional representations of objects

T. Saanum, L. M. Schulze Buschoff, P. Dayan, E. Schulz

Paper

ICML 2023

The Acquisition of Physical Knowledge in Generative Neural Networks

L. M. Schulze Buschoff, E. Schulz, M. Binz

Paper

ICLR 2022

Trivial or Impossible—dichotomous data difficulty masks model differences (on ImageNet and beyond)

K. Meding*, L. M. Schulze Buschoff*, R. Geirhos, F. A. Wichmann

Paper

NeurIPS Workshop 2021

ImageNet suffers from dichotomous data difficulty

K. Meding*, L. M. Schulze Buschoff*, R. Geirhos, F. A. Wichmann

Paper