A GRPO-based reinforcement learning framework teaches an MLLM to propose zoom-in regions, improving small-object detection and interactive segmentation under a fixed sensing budget.
Animate vision.Artificial intelligence, 48(1):57–86, 1991
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
A GRPO-based reinforcement learning framework teaches an MLLM to propose zoom-in regions, improving small-object detection and interactive segmentation under a fixed sensing budget.