← Back to the directory

Company · Works with The Hong Kong University of Science and Technology, Tsinghua University

Noiz AI


Coverage1

Release · Aug 17, 2026

Noiz AI Releases HelixWorld 1.0, a Real-Time Interactive Audio-Visual World Model

Noiz AI, with The Hong Kong University of Science and Technology, Tsinghua University, Carnegie Mellon University, and Google DeepMind, has released HelixWorld 1.0, a real-time interactive audio-visual world model. It generates 24 FPS video and 48 kHz stereo audio together through a native Transformer, supporting interactive world exploration rather than fixed clips. Model weights and code are to be fully open-sourced in the coming weeks, according to the release.

Original sources (Chinese)

终于!世界模型进入“有声时代”:24FPS画面+48kHz立体声实时生成qbitai