paper-with-me

Papers

Efficient Architectures for High Resolution Vision-Language Models

2025-01-05 · Miguel Carvalho, Bruno Martins

Vision-Language Models (VLMs) have recently experienced significant advancements. However, challenges persist in the accurate recognition of fine details within high resolution images, which limits performance in multiple tasks. This work introduces Pheye, a novel architecture that efficiently processes high-resolution images while training fewer parameters than similarly sized VLMs. Notably, Pheye achieves a high efficiency while maintaining strong performance, particularly in tasks that demand fine-grained image understanding and/or the handling of scene-text.

📄 PDF Abstract BibTeX arXiv:2501.02584

Code (1)

miguelscarv/pheye 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images

2025-07-17 · Zahra Tehraninasab, Amar Kumar, Tal Arbel

Medical image synthesis presents unique challenges due to the inherent complexity and high-resolution details required in clinical contexts. Traditional generative architectures such as Generative Adversarial Networks (G…

Data AugmentationImage GenerationMedical Image Generation

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

2024-03-04 · Yuchen Duan, Weiyun Wang, Zhe Chen, Xizhou Zhu 외

Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper…

image-classificationImage Classification

Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs

2025-10-15 · Mustafa Munir, Alex Zhang, Radu Marculescu arxiv

Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction method…

Semantic SegmentationImage Classification

Win-Win: Training High-Resolution Vision Transformers from Two Windows

2023-10-01 · Vincent Leroy, Jerome Revaud, Thomas Lucas, Philippe Weinzaepfel

Transformers have become the standard in state-of-the-art vision architectures, achieving impressive performance on both image-level and dense pixelwise tasks. However, training vision transformers for high-resolution pi…

Depth EstimationDepth PredictionOptical Flow EstimationSemantic Segmentation

Vision-Enhanced Large Language Models for High-Resolution Image Synthesis and Multimodal Data Interpretation

2025-12-14 · Karthikeya KV arxiv

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and m…