3 papers
cs.RO2026
VL-MemKnG: Hybrid Memory with a Spatio-Temporal Knowledge Graph for Question Answering over Long Egocentric Navigation Trajectories
Svetlana Lukina, Mohamad Al Mdfaa, Gloria Haro +2
Answering navigation-relevant questions over long egocentric videos requires retrieving and organizing evidence distributed across distant temporal moments while maintaining spatia…
cs.RO2026
Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering
Mohamad Al Mdfaa, Svetlana Lukina, Timur Akhtyamov +4
Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memor…
cs.CV2026
Mapping the Unseen: Unified Promptable Panoptic Mapping with Dynamic Labeling using Foundation Models
Mohamad Al Mdfaa, Raghad Salameh, Geesara Kulathunga +2
Panoptic maps enable robots to reason about both geometry and semantics. However, open-vocabulary models repeatedly produce closely related labels that split panoptic entities and…