# Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models

arXiv: https://arxiv.org/abs/2501.14276 · HTML: https://mlsanity.com/paper/2501.14276/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 48 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 11 of 11)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024)
- [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](https://mlsanity.com/paper/2405.20797/) (2024)
- [Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2408.15556/) (2024)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)

## Built on by (most cited first, 4 of 4)

- [HRVVS: A High-resolution Video Vasculature Segmentation Network via Hierarchical Autoregressive Residual Priors](https://mlsanity.com/paper/2507.22530/) (2025)
- [Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance](https://mlsanity.com/paper/2509.15704/) (2025)
- [MARVIS: Modality Adaptive Reasoning over VISualizations](https://mlsanity.com/paper/2507.01544/) (2025)
- [Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality](https://mlsanity.com/paper/2507.20156/) (2025)

## Abstract (arXiv)

As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing. However, existing partitioning methods uniformly process sub-images, resulting in suboptimal image understanding. In this work, we reveal that the sub-images with higher semantic relevance to the entire image encapsulate richer visual information for preserving the model's visual understanding ability. Therefore, we propose the Global Semantic-guided Weight Allocator (GSWA) module, which dynamically allocates weights to sub-images based on their relative information density, emulating human visual attention mechanisms. This approach enables the model to focus on more informative regions, overcoming the limitations of uniform treatment. We integrate GSWA into the InternVL2-2B framework to create SleighVL, a lightweight yet high-performing model. Extensive experiments demonstrate that SleighVL outperforms models with comparable parameters and remains competitive with larger models. Our work provides a promising direction for more efficient and contextually aware high-resolution image processing in LVLMs, advancing multimodal system development.