BOP-ASK supplies 150k images and 33M QA pairs across six tasks to improve VLMs on precise 3D object interaction reasoning and spatial planning.
Cambrian-1: A fully open, vision-centric exploration of multimodal llms, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BOP-ASK: Object-Interaction Reasoning for Vision-Language Models
BOP-ASK supplies 150k images and 33M QA pairs across six tasks to improve VLMs on precise 3D object interaction reasoning and spatial planning.