A collaborative Planning-Perception agent framework using MLLMs constructs a holistic cognitive map through iterative viewpoint supplementation and achieves reported SOTA gains on six 3D benchmarks.
arXiv preprint arXiv:2504.08307 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Agentic Collaborative Cognition for Zero-Shot 3D Understanding
A collaborative Planning-Perception agent framework using MLLMs constructs a holistic cognitive map through iterative viewpoint supplementation and achieves reported SOTA gains on six 3D benchmarks.