EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$
While Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in standard visual understanding, adapting them for active visual search in 360$^\circ$ panoramic environments exposes fundamental limitations. Specifically, standard MLLMs struggle to effectively model inherent panoramic properties, such as severe polar distortion and continuous cylindrical topologies, which significantly degrades target detection accuracy. Consequently, existing panoramic search methods attempt to compensate by relying heavily on fragmented local viewpoints. Burdened by rigid initializa
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Embed the world: Multimodal AI for searchable aerial imagery at scale →
- PossiblePossibly related (embedding) · 46%vlm-starter →
- PossiblePossibly related (embedding) · 46%VioletVision-3B →
- LinkedLinked via arxiv author · 85%Jingtao Xu →
“EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$”
- LinkedLinked via arxiv author · 85%Zizhuo Lin →
“EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$”
- LinkedLinked via arxiv author · 85%Jianwen Sun →
“EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$”
- LinkedLinked via arxiv author · 85%Yi Yang →
“EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$”
- LinkedLinked via arxiv author · 85%Yawei Luo →
“EAGLE-360: Embodied Active Global-to-Local Exploration in 360$^\circ$”