Saved in:
Bibliographic Details
Main Authors: Zheng, Lihao, Shao, Zhenwei, Zhou, Yu, Yang, Yan, Shen, Xintian, Chen, Jiawei, Ma, Hao, Wei, Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22498
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918466249818112
author Zheng, Lihao
Shao, Zhenwei
Zhou, Yu
Yang, Yan
Shen, Xintian
Chen, Jiawei
Ma, Hao
Wei, Tao
author_facet Zheng, Lihao
Shao, Zhenwei
Zhou, Yu
Yang, Yan
Shen, Xintian
Chen, Jiawei
Ma, Hao
Wei, Tao
contents Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object constancy. In addition, existing approaches typically rely on expensive human annotations or large-scale chain-of-thought (CoT) data generation. We propose Compositional Grounded Contrast (abbr. CGC), a low-cost full framework for boosting fine-grained multi-image understanding of MLLMs. Built on existing single-image grounding annotations, CGC constructs compositional multi-image training instances through Inter-Image Contrast and Intra-Image Contrast, which introduce semantically decoupled distractor contexts for cross-image discrimination and correlated cross-view samples for object constancy, respectively. CGC further introduces a Rule-Based Spatial Reward within the GRPO framework to improve source-image attribution, spatial alignment, and structured output validity under a Think-before-Grounding paradigm. Experiments show that CGC achieves state-of-the-art results on fine-grained multi-image benchmarks, including MIG-Bench and VLM2-Bench. The learned multi-image understanding capability also transfers to broader multimodal understanding and reasoning tasks, yielding consistent gains over the Qwen3-VL-8B base model on MathVista (+2.90), MuirBench (+2.88), MMStar (+1.93), MMMU (+1.77), and BLINK (+1.69).
format Preprint
id arxiv_https___arxiv_org_abs_2604_22498
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
Zheng, Lihao
Shao, Zhenwei
Zhou, Yu
Yang, Yan
Shen, Xintian
Chen, Jiawei
Ma, Hao
Wei, Tao
Computer Vision and Pattern Recognition
Artificial Intelligence
Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object constancy. In addition, existing approaches typically rely on expensive human annotations or large-scale chain-of-thought (CoT) data generation. We propose Compositional Grounded Contrast (abbr. CGC), a low-cost full framework for boosting fine-grained multi-image understanding of MLLMs. Built on existing single-image grounding annotations, CGC constructs compositional multi-image training instances through Inter-Image Contrast and Intra-Image Contrast, which introduce semantically decoupled distractor contexts for cross-image discrimination and correlated cross-view samples for object constancy, respectively. CGC further introduces a Rule-Based Spatial Reward within the GRPO framework to improve source-image attribution, spatial alignment, and structured output validity under a Think-before-Grounding paradigm. Experiments show that CGC achieves state-of-the-art results on fine-grained multi-image benchmarks, including MIG-Bench and VLM2-Bench. The learned multi-image understanding capability also transfers to broader multimodal understanding and reasoning tasks, yielding consistent gains over the Qwen3-VL-8B base model on MathVista (+2.90), MuirBench (+2.88), MMStar (+1.93), MMMU (+1.77), and BLINK (+1.69).
title CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.22498