Quanta AI Labs

CASIA (Institute of Automation) · Research Paper

PhiZero

CASIA's reason-then-render world model first predicts future physics as a discrete 'physical language' sequence (256 tokens, 175x compression vs raw VAE tokens) built on a Qwen3-VL-4B reasoner, then renders it to video via diffusion. Leads on Physics-IQ (41.2), PhyGround (3.01) and IntPhys2 (56.34); code not yet released.

Open the source ↗

Similar Research & Safety releases

  • Dream-RSI

    Google, DeepMind, Maryland & Virginia · Recursive Self-Improvement · Week 39, 2026

  • WeatherNext 3

    Google DeepMind · WeatherNext 3 · Week 36, 2026

  • mdlARC

    Mithil Vakde · Efficient ARC-AGI Model · Week 36, 2026

  • WikiSkill

    Tang, Rashtchian, Ferng, Tomkins, Juan and Vu · Skill Evolution · Week 36, 2026

  • Planetary Prediction Engine

    Google Research · Planetary Prediction · Week 35, 2026

  • DiffusionOPSD

    ByteDance Seed · Diffusion Training · Week 35, 2026

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.