Robbyant Unveils LingBot-Depth 2.0 and LingBot-Vision to Redefine Robotic Spatial Perception

Glass crashes slashed? Ant Group AI unit claims robot sensing advance

New perception model for embodied AI surpasses dominant rival from Meta Platforms at smaller scale with less training, firm claims.

Robbyant Unveils LingBot-Depth 2.0 and LingBot-Vision to Redefine Robotic Spatial Perception

SHANGHAI — Robbyant, an embodied AI company within Ant Group, today announced the launch of LingBot-Depth 2.0, a next-generation spatial perception model, alongside its foundational visual model, LingBot-Vision. This release marks a significant leap in robotic spatial perception, empowering robots to accurately understand and navigate the physical world. From “Seeing” to “Seeing Accurately” Building upon […]

Ant Group’s Robbyant Open-Sources LingBot-Vision: A 1B Boundary-Centric Vision Foundation Model for Dense Spatial Perception

Robbyant's LingBot-Vision is an open-source 1B boundary-centric vision foundation model that leads NYU-Depth v2 RMSE, ahead of DINOv3.

Robbyant launches LingBot-Depth 2.0 and LingBot-Vision for advanced robotic spatial perception

Robbyant, an embodied AI company within Ant Group, has announced the launch of LingBot-Depth 2.0, a next-generation spatial perception model, alongside its foundational visual model, LingBot-Vision. This release marks a significant leap in robotic spatial perception, empowering robots to accurately understand and navigate the physical world. From ‘seeing’ to ‘seeing accurately’ Building upon the success […]

Ant Group's LingBot-Vision Claims 12 World Firsts: 1.1B Parameter Model Beats 7B DINOv3

Ant Group's LingBot (蚂蚁灵波) has unveiled LingBot-Depth 2.0, a spatial perception model that achieves 12 world-first results across public and private benchmark datasets. The model's underlying technology, the LingBot-Vision foundation model, represents the world's first spatial-native vision foundation model purpose-built for embodied AI, and has been released as open source.LingBot-Vision is a paradigm shift from conventional computer vision fou…