SpatiO uses heterogeneous vision-language agents with test-time orchestration to dynamically weight their contributions for improved spatial reasoning on benchmarks like 3DSRBench and CV-Bench.
Title resolution pending
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
-
SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning
SpatiO uses heterogeneous vision-language agents with test-time orchestration to dynamically weight their contributions for improved spatial reasoning on benchmarks like 3DSRBench and CV-Bench.