collaborators

1 paper

cs.CV2026

GVT3D: Gesture-Vision-Text Token Enrichment for 3D Embodied Reference Understanding

Vimarsh Shah, Dulanga Weerakoon, Ajinkya Deshpande +9

Natural human-robot interaction requires robots to interpret language and gestures within a 3D environment to support tasks such as pick-and-place and object retrieval. 3D Embodied…