LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917549995720704 |
|---|---|
| author | Shen, Yuxiang Huang, Hailong Gao, Zhenkun Li, Xueheng Zhou, Man Xie, Chengjun Che, Haoxuan He, Xuanhua Zhang, Jie |
| author_facet | Shen, Yuxiang Huang, Hailong Gao, Zhenkun Li, Xueheng Zhou, Man Xie, Chengjun Che, Haoxuan He, Xuanhua Zhang, Jie |
| contents | Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose LookWise, a framework for adaptive visual reasoning. LookWise follows a two-stage pipeline: a confidence-based module decides when to look more carefully, and a semantic-guided localization module determines where to look. This design enables MLLMs to adaptively acquire fine-grained visual evidence without additional training. Experiments on fine-grained and high-resolution visual reasoning benchmarks show that LookWise consistently improves accuracy over strong baselines while achieving an approximately $4.0\times$ inference speedup over the search-based method ZoomEye, demonstrating robust cross-model generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00171 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models Shen, Yuxiang Huang, Hailong Gao, Zhenkun Li, Xueheng Zhou, Man Xie, Chengjun Che, Haoxuan He, Xuanhua Zhang, Jie Computer Vision and Pattern Recognition Artificial Intelligence Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose LookWise, a framework for adaptive visual reasoning. LookWise follows a two-stage pipeline: a confidence-based module decides when to look more carefully, and a semantic-guided localization module determines where to look. This design enables MLLMs to adaptively acquire fine-grained visual evidence without additional training. Experiments on fine-grained and high-resolution visual reasoning benchmarks show that LookWise consistently improves accuracy over strong baselines while achieving an approximately $4.0\times$ inference speedup over the search-based method ZoomEye, demonstrating robust cross-model generalization. |
| title | LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.00171 |