Machine Heart
Jul 10, 2026 · Artificial Intelligence
LingBot-VA 2.0 Introduces the First Embodied‑Native Pre‑Training Model for Robotics
LingBot-VA 2.0 presents an industry‑first embodied‑native pre‑training model that aligns video prediction with action generation, uses a semantic‑visual‑action tokenizer, multi‑chunk prediction, foresight reasoning, and a sparse MoE architecture to achieve higher success rates and up to 6.5× faster end‑to‑end inference on real‑world robot tasks.
Foresight ReasoningInference AccelerationMulti‑Chunk Prediction
0 likes · 17 min read
