Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.09498 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915287329144832 |
|---|---|
| author | Zhang, Bo Li, Shuo Tian, Runhe Yang, Yang Tang, Jixin Zhou, Jinhao Ma, Lin |
| author_facet | Zhang, Bo Li, Shuo Tian, Runhe Yang, Yang Tang, Jixin Zhou, Jinhao Ma, Lin |
| contents | In this paper, we introduce Flash-VL 2B, a novel approach to optimizing Vision-Language Models (VLMs) for real-time applications, targeting ultra-low latency and high throughput without sacrificing accuracy. Leveraging advanced architectural enhancements and efficient computational strategies, Flash-VL 2B is designed to maximize throughput by reducing processing time while maintaining competitive performance across multiple vision-language benchmarks. Our approach includes tailored architectural choices, token compression mechanisms, data curation, training schemes, and a novel image processing technique called implicit semantic stitching that effectively balances computational load and model performance. Through extensive evaluations on 11 standard VLM benchmarks, we demonstrate that Flash-VL 2B achieves state-of-the-art results in both speed and accuracy, making it a promising solution for deployment in resource-constrained environments and large-scale real-time applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09498 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput Zhang, Bo Li, Shuo Tian, Runhe Yang, Yang Tang, Jixin Zhou, Jinhao Ma, Lin Computer Vision and Pattern Recognition Artificial Intelligence In this paper, we introduce Flash-VL 2B, a novel approach to optimizing Vision-Language Models (VLMs) for real-time applications, targeting ultra-low latency and high throughput without sacrificing accuracy. Leveraging advanced architectural enhancements and efficient computational strategies, Flash-VL 2B is designed to maximize throughput by reducing processing time while maintaining competitive performance across multiple vision-language benchmarks. Our approach includes tailored architectural choices, token compression mechanisms, data curation, training schemes, and a novel image processing technique called implicit semantic stitching that effectively balances computational load and model performance. Through extensive evaluations on 11 standard VLM benchmarks, we demonstrate that Flash-VL 2B achieves state-of-the-art results in both speed and accuracy, making it a promising solution for deployment in resource-constrained environments and large-scale real-time applications. |
| title | Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.09498 |