WALL-SS

A next-scale autoregressive world model from ZiVariable Robotics that simulates robot observation-action sequences and rolls out future states for testing robot policies.

What we have written

• WALL-SS puts robot simulation on trial in the real world2026-09-10

  WALL-SS simulates 60-second tasks such as pouring water and organizing objects, then compares the outcomes of different actions before a robot acts. ifanr reports that its team also retained data from missed grasps, slips, collisions, re-grasps, manual takeovers, and recovery attempts.

• WALL-SS turns AI output into a testable world2026-09-02

  Loopit's Zing-0.5 is a useful marker for where AI output is moving: away from static clips and toward worlds that accept input. They keep state. They can be tested. woshipm reports that Loopit calls its route "calculate the world first, then generate the world," which puts rules before spectacle. Th

Where it came from

The Chinese reporting these articles are built from. Read in Chinese; the facts are ours to restate, the words are not.

• 从课件到具身智能实验室，AI开始帮老师生成教学应用36kr
• 世界模型进入下半场：自变量 WALL-SS 突破三大瓶颈，让虚拟世界成为机器人的「训练场」geekpark
• 人类，越来越难理解 AIgeekpark
• 「AstraTennis」时刻：机器人在全球直播中打了一场真正的网球geekpark
• 机器人运动会散场后，自变量给机器人建了一座「虚拟训练场」ifanr
• 智元机器人「奥运」首秀封神，戴着工牌狂揽 18 枚金牌ifanr
• 以前我以为AI产品拼的是模型，直到我研究了Terafabwoshipm
• 前沿大模型都在拼代码，真正争夺的不是编程能力，而是下一代模型的创造权woshipm
• 美国红杉预言的模应一体，Loopit是值得重点关注的样本woshipm
• 对话郭人杰：在绝对0-1的赛道里，家庭具身智能没有大哥woshipm
• 如何设计自然的具身人机交互woshipm
• 从人形概念到咖啡机器人，具身智能如何跨过商业化鸿沟woshipm

All tools - how we work.