collaborators

11 papers

cs.CV2026

CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models

Souptik Kumar Majumdar, Fabian Kögel, Andreas Bulling

Linear probes and activation steering have uncovered that vision-language models (VLMs) internally represent mental states such as agents' beliefs, knowledge, and intentions. Howev…

cs.CV2026

CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning

Lei Shi, Andreas Bulling

We propose CLAD, a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos. Procedure planning is the challenging task of predictin…

cs.LG2026

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei +2

We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly a…

cs.LG2026

High entropy leads to symmetry-equivariant policies in Dec-POMDPs

Johannes Forkel, Constantin Ruhdorfer, Michael Beukman +2

We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initia…

cs.AI2026

The Yokai Learning Environment: Tracking Beliefs Over Space and Time

Constantin Ruhdorfer, Matteo Bortoletto, Johannes Forkel +2

The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm…

cs.CL2025

ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions

Matteo Bortoletto, Constantin Ruhdorfer, Andreas Bulling

Most existing Theory of Mind (ToM) benchmarks for foundation models rely on variations of the Sally-Anne test, offering only a very limited perspective on ToM and neglecting the co…