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...

Deskribapen osoa

Xehetasun bibliografikoak

Egile nagusia:	Wagner, Royden
Formatua:	Online
Hizkuntza:	ingelesa
Argitaratua:	KIT Scientific Publishing 2026
Gaiak:	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
Sarrera elektronikoa:	ONIX_20260519T105721_9783731514749_14
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!