Preprint
Aug 2026
AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models
AlloEgo-VLM is developed, a framework to disambiguate allocentric and egocentric reference frames, even under ambiguous queries, and to be easily integrated into existing VLMs via supervised fine-tuning.
Kuan-Lin Chen, Tzu-Ti Wei, Chao-Chi Liao et al.
· 0 citations