VASA is a vision-guided agent for open ad-hoc segmentation that creates and validates masks through planning, tool use, and error recovery, outperforming baselines on the new PARS benchmark and RefCOCOm.
StAR: Segment anything reasoner
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
B-GRTO pre-trains a segmentation tool via bootstrapped group relative optimization on GRPO rollouts, yielding substantial gains over plain GRPO on referring segmentation benchmarks.
citing papers explorer
-
Vision Harnessing Agent for Open Ad-hoc Segmentation
VASA is a vision-guided agent for open ad-hoc segmentation that creates and validates masks through planning, tool use, and error recovery, outperforming baselines on the new PARS benchmark and RefCOCOm.
-
B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation
B-GRTO pre-trains a segmentation tool via bootstrapped group relative optimization on GRPO rollouts, yielding substantial gains over plain GRPO on referring segmentation benchmarks.