Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 1
Magistrsko delo
Oznake: VLA;ViT;Flow Matching;Robotics;Visual-Language-Action;multi-modal perception;robot manipulation;
Vision-language-action (VLA) models are end-to-end robot control models that inherit rich perceptual representations from pretrained vision-language foundation models. However, it remains unclear whether these representations are fully exploited during action generation. This work investigates wheth ...
Leto: 2026 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Št. zadetkov: 1
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: