Robbyant, the embodied-AI company within Ant Group, has open-sourced LingBot-Vision, a family of self-supervised Vision Transformers built for dense spatial perception, with weights shipped under Apache-2.0 on Hugging Face in four sizes — ViT-giant, ViT-large, ViT-base, and ViT-small — alongside a technical report and inference code. LingBot-Vision treats boundaries as a native pretraining signal, and the flagship ViT-g/16 has roughly 1.1B parameters, trained with a new objective called masked boundary modeling on a curated corpus of about 161M images — selected from a 2B web pool — with no human labels, no external edge detectors, and no pretrained backbone. The model consumes less than a third of DINOv3’s training samples, and the flagship is distilled into ViT-L (300M), ViT-B (86M), and ViT-S students that lead dense prediction within their size classes. The method builds on the DINO/iBOT self-distillation paradigm, using boundary-forcing where the teacher predicts a dense boundary field online and identifies boundary-bearing tokens B, which are forced into the student’s masked set on top of the random mask M, giving the combined mask M⁺ = M ∪ B. Masked tokens are then routed by geometry: boundary tokens receive an explicit geometric target in addition to the semantic self-distillation target, while interior masked