Models · MarkTechPost ·
Ant Group’s Robbyant Unveils LingBot-VA 2.0: A Causal Video-Action Model Built Natively for Physical AI
Ant Group's Robbyant released the LingBot-VA 2.0 technical report, describing a Physical AI video-action foundation model built natively for embodiment. The system uses Foresight Reasoning and asynchronous control, and the report highlights a causal DiT, sparse-MoE video stream, and semantic visual-action tokenizer.