Interpretable Representation Learning for Motion Forecasting

We address interpretable representation learning for motion forecasting in self-driving cars. Rather than treating transformers as black boxes, we develop methods to interpret and modify learned representations. We introduce self-supervised pre-training with interpretable objectives. Moreover, we pr...

Descripción completa

Detalles Bibliográficos

Autor principal:	Wagner, Royden
Formato:	Online
Lenguaje:	inglés
Publicado:	KIT Scientific Publishing 2026
Materias:	Autonomes Fahren Bewegungsvorhersage Maschinelles Lernen Mechanistic interpretability Motion forecasting Representation learning Self-driving cars Transformer models thema EDItEUR::U Computing and Information Technology::UY Computer science
Acceso en línea:	ONIX_20260519T105721_9783731514749_14
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!