Today for AI
HOT RADAR
llmHEAT 11.8°

AI CURATED HOT STORY · 11/10/2026

Zhiyuan AI Unveils WITA-Omni Embodied Omni-Modal Interaction Model

1 reports archived1 independent sourcesupdated 11/10/2026, 19:24:05
Synthesis & Latest Updates
1 Sources Cross-Validated

Zhiyuan AI has released WITA-Omni, billed as the industry's first embodied omni-modal end-to-end interaction model, adding tactile and proprioceptive inputs plus robot action and facial-expression outputs beyond audio and video. Built on a streaming full-duplex architecture, it delivers interaction latency as low as roughly 400 ms and about 600 ms on average, nearly 3x faster than industry norms, while supporting wake-word-free omni-modal rejection and streaming simultaneous interpretation across 100+ languages and dialects.

LATEST/Zhiyuan AI has released WITA-Omni, billed as the industry's first embodied omni-modal end-to-end interaction model, adding tactile and proprioceptive inputs plus robot action and facial-expression outputs beyond audio and video. Built on a streaming full-duplex architecture, it delivers interaction latency as low as roughly 400 ms and about 600 ms on average, nearly 3x faster than industry norms, while supporting wake-word-free omni-modal rejection and streaming simultaneous interpretation across 100+ languages and dialects.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·78 pts

    Zhiyuan AI Unveils WITA-Omni Embodied Omni-Modal Interaction Model

    • Adds tactile and proprioceptive inputs plus action and expression outputs as an interaction brain for the physical world
    • Streaming full-duplex architecture enables listen-think-respond-act simultaneously, with latency down to ~400 ms and ~600 ms average
    • Omni-modal rejection fuses orientation, voiceprint, lip motion and pose for wake-word-free dialogue with fewer false triggers