Ant Group's Robbyant open-sources LingBot-Vision: a 1B-parameter boundary-centric vision foundation model for dense spatial perception
Original title:Ant Group’s Robbyant Open-Sources LingBot-Vision: A 1B Boundary-Centric Vision Foundation Model for Dense Spatial Perception
AI summary
Robbyant, Ant Group's embodied intelligence company, has open-sourced LingBot-Vision, a family of self-supervised vision Transformers designed for dense spatial perception. The flagship ViT-g/16 has about 1.1B parameters and is trained with masked boundary modeling, treating boundaries as a native pretraining signal. On dense spatial tasks, the 1B model matches or surpasses models up to 7x larger (such as 7B DINOv3). The models are open-sourced on Hugging Face under the Apache-2.0 license in four sizes: ViT-g, ViT-L (300M), ViT-B (86M), and ViT-S.
Key Takeaways
- Robbyant,Ant Group's embodied intelligence company,has open-sourced LingBot-Vision,a family of…
- The flagship ViT-g/16 has about 1.
- 1B parameters and is trained with masked boundary modeling,treating boundaries as a native…
- On dense spatial tasks,the 1B model matches or surpasses models up to 7x larger (such as 7B DINOv3).
- The models are open-sourced on Hugging Face under the Apache-2.
Quick Facts
- Published
- Updated
- Source
- MarkTechPost(RSS)
- Category
- Model Releases
- AI score
- 71
在视觉基础模型里把边界当作核心信号,这个思路很反常识,1B模型在深度估计上超过7B的DINOv3,做机器人的可以认真看看。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Ant Group's Robbyant open-sources LingBot-Vision: a 1B-parameter boundary-centric vision foundation model for dense spatial perception. July 8, 2026. https://new.nat6.net/en/news/cmrbikwbz04b5ihl16qfp5ntw/