GRIT introduces a grounded reasoning paradigm for MLLMs where reasoning chains interleave text and bounding boxes, trained via GRPO-GR reinforcement learning on as few as 20 examples without annotations.
Unsupervised visual chain-of-thought reasoning via preference optimization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2025 4representative citing papers
CropVLM uses reinforcement learning to learn image zooming policies that boost fine-grained perception in VLMs on out-of-domain high-resolution tasks without labeled boxes, synthetic data, or VLM changes.
HiDe uses token-wise attention decoupling and layout-preserving decoupling to build compact crops that push Qwen2.5-VL and InternVL3 to state-of-the-art scores on high-resolution VQA benchmarks.
LaV-CoT introduces a multi-stage visual CoT pipeline and GRPO training with language-consistency rewards, delivering up to 9.5% accuracy gains on multilingual VQA benchmarks over similar-sized open models.
citing papers explorer
-
GRIT: Teaching MLLMs to Think with Images
GRIT introduces a grounded reasoning paradigm for MLLMs where reasoning chains interleave text and bounding boxes, trained via GRPO-GR reinforcement learning on as few as 20 examples without annotations.
-
CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
CropVLM uses reinforcement learning to learn image zooming policies that boost fine-grained perception in VLMs on out-of-domain high-resolution tasks without labeled boxes, synthetic data, or VLM changes.
-
HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
HiDe uses token-wise attention decoupling and layout-preserving decoupling to build compact crops that push Qwen2.5-VL and InternVL3 to state-of-the-art scores on high-resolution VQA benchmarks.
-
LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
LaV-CoT introduces a multi-stage visual CoT pipeline and GRPO training with language-consistency rewards, delivering up to 9.5% accuracy gains on multilingual VQA benchmarks over similar-sized open models.