Tag
LingBot Vision, a self-supervised vision backbone family from Ant Group, uses masked boundary modeling to achieve state-of-the-art performance on dense spatial perception tasks, beating the larger DINOv3 model on NYU-Depth v2.
Progress update on DSpark: training of DFlash backbone and markov head is complete, enabling use on 27B. Next is training the confidence head for adaptive drafting, expected 8-14% speed improvement over DFlash.