Large multimodal models display emerging but limited spatial action capabilities in goal-oriented urban 3D navigation, remaining far from human-level performance with errors diverging rapidly after critical decision points.
Sigurdsson, Robinson Piramuthu, Jesse Thomason, and Gaurav S
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
DarkQA is a new benchmark that measures vision-language model performance on basic visual questions under controlled low-light degradations modeled from real camera physics.
NORM-Nav is a zero-shot framework that parses natural language behavioral constraints with an LLM, grounds them via vision-LiDAR, and encodes them as multi-layer costmaps for grid-based robot navigation.
FineCog-Nav uses fine-grained cognitive modules driven by foundation models to outperform zero-shot baselines in UAV navigation and introduces the AerialVLN-Fine benchmark with refined instructions.
Uni-NaVid unifies diverse embodied navigation tasks into one video-based vision-language-action model trained on 3.6 million samples from four sub-tasks, achieving state-of-the-art performance on benchmarks and real-world tests.
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
citing papers explorer
-
How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace
Large multimodal models display emerging but limited spatial action capabilities in goal-oriented urban 3D navigation, remaining far from human-level performance with errors diverging rapidly after critical decision points.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.