A two-stage RL method with information gaps and grounding loss trains MLLMs to focus on and precisely crop relevant image regions, yielding SOTA results on high-resolution VQA benchmarks.
In the first example, while both mod- els correctly crop the flag, DeepEyes provides an incorrect answer, whereas Stage-I arrives at the correct one
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
-
Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs
A two-stage RL method with information gaps and grounding loss trains MLLMs to focus on and precisely crop relevant image regions, yielding SOTA results on high-resolution VQA benchmarks.