3 papers
cs.RO2026
Studying the Effect of Explicit Interaction Representations on Learning Scene-level Distributions of Human Trajectories
Anna Mészáros, Javier Alonso-Mora, Jens Kober
Effectively capturing the joint distribution of all agents in a scene is relevant for predicting the true evolution of the scene and in turn providing more accurate information to…
cs.LG2025
Out-of-distribution Tests Reveal Compositionality in Chess Transformers
Anna Mészáros, Patrik Reizinger, Ferenc Huszár
Chess is a canonical example of a task that requires rigorous reasoning and long-term planning. Modern decision Transformers - trained similarly to LLMs - are able to learn compete…
cs.LG2025
STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction models
Julian F. Schumann, Anna Mészáros, Jens Kober +1
While trajectory prediction plays a critical role in enabling safe and effective path-planning in automated vehicles, standardized practices for evaluating such models remain under…