Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
Paper
•
2509.25794
•
Published
•
1
pio
pio-benchmark
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models
in Multi-Stage Visual Grounding
updated
a dataset
8 months ago
pio-benchmark/PIO
liked
a dataset
8 months ago
pio-benchmark/PIO
Organizations
None yet
upvoted
a
paper
about 1 month ago