**From Pixels to Words -- Towards Native One-Vision Models at Scale** > Current

**From Pixels to Words -- Towards Native One-Vision Models at Scale**

> Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragments pixel-level signals across frames and scatters early pixel-word interactions. In parallel, native VLMs, despite impressive performance on single images, remain largely unexplored in multi-image, video understanding, and spatial intellige...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：ai-models
- **发布时间**：2026-05-28 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2605.28820)