collaborators

28 papers

cs.LG2026

Clustered Randomized Smoothing for Stochastic Prediction Functions

Eduardo Figueiredo, Frederik Mathiesen, Julian Schumann +3

Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions a critical r…

cs.AI2026

Emotion in an active inference model of human driving

Julian F. Schumann, Johan Engström, Ran Wei +3

Active inference has emerged as a principled framework for modeling adaptive behavior by balancing goal-directed action with uncertainty reduction. It has been successfully applied…

cs.RO2026

Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections

Zhaoting Li, Gang Chen, Javier Alonso-Mora +2

Diffusion policies have recently emerged as a powerful framework for robotic manipulation. However, like other behavior cloning methods, they remain vulnerable to distributional sh…

cs.RO2026

Active inference as a unified model of collision avoidance behavior in human drivers

Julian F. Schumann, Johan Engström, Leif Johnson +4

Collision avoidance -- involving a rapid threat detection and quick execution of the appropriate evasive maneuver -- is a critical aspect of driving. However, existing models of hu…

cs.AI2026

Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model

Julian F. Schumann, Johan Engström, Ran Wei +3

Understanding how road users resolve space-sharing conflicts is important both for traffic safety and the safe deployment of autonomous vehicles. While existing models have capture…

cs.RO2026

From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback

Zhaoting Li, Rodrigo Pérez-Dattari, Robert Babuska +2

Behavior cloning (BC) optimizes policies by treating human demonstrations as pointwise action labels. While effective with accurate action labels, this formulation is brittle in pr…