WeVisOne-VL: Unified model for fine-grained visual perception
In brief
- WeVisOne-VL unifies object detection and pixel-level perception via structured next-token prediction.
- The model handles 6 visual tasks including segmentation, OCR and matting with a single architecture.
- It outperforms existing VLMs on over 30 benchmarks while rejecting queries with no object.
Researchers introduce WeVisOne-VL, a unified vision-language model handling visual perception tasks from object-level to pixel-level. According to the announcement, it combines object detection, referring localization, counting, OCR, segmentation, and matting through structured next-token prediction. The model is trained in three stages with mixed-task reinforcement learning and outperforms existing VLMs on over 30 benchmarks.
This summary gives you the essentials. The full article, its figures and quotes are on Hugging Face Daily Papers.
Read the original articleAI-generated summary of the source, checked by rules. How we write · Report an error