**UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language

**UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models**

> Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge devices. While efforts to compress LVLMs focus heavily on vision token reduction or smaller language models, the vision encoder is largely overlooked, typically deployed as a monolithic, computationally heavy feature extractor. Moreover, there is no previous effort tha...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：论文
- **发布时间**：2026-07-28 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2607.23373)