Muka Robotics' LJM Model Ranks 2nd Globally in Embodied World Model Arena
机器之心 · wechat · 2026-07-30
Startup Muka Robotics, founded less than four months ago, proposed the Latent Joint-conditional Model (LJM). Trained with only 32 GPUs, it ranked 2nd globally on the authoritative WorldArena benchmark and achieved SOTA on four visual metrics of the LIBERO benchmark.
LJM uses a "dual-brain" architecture separating physical interaction reasoning from future video rendering. A reasoning expert predicts specific physical changes in the latent space, while a world modeling expert renders the video. This solves the flaw of traditional video models prioritizing visuals over physical interaction. Experiments prove that strong video priors alone are insufficient for robotic world models.
More from Embodied
- 1X CEO Reiterates Promise: Humanoid Robot Neo to Support Full Autonomy by Year-End Delivery — ChrisGPT · 2026-07-30
- Google Gemini Robotics Set for Major 2.0 Update — CyberRobooo · 2026-07-30
- Google Teases New AI Photography Experiences Coming to Pixel 11 Pro — docmilanfar · 2026-07-30
- Handroid: A Reconfigurable Robot Shifting Between Humanoid and Dexterous Hand — carlosdponx · 2026-07-30
- RATs: Multi-Agent Robot Lifelong Skill Learning Without Gradients or RL — rsasaki0109 · 2026-07-30
- Prediction Is Not Perception: Why Video Models Fall Short for Embodied AI — PierceLilholt · 2026-07-30