Release of GO-3 Preview embodied foundation model with WRAM architecture
Overview
Yao Maoqing, co-founder and president of Zhiyuan, stated that general-purpose large models lack the efficiency and low-level physical control required for real-world robotics. He proposed a layered architecture where general models handle high-level planning, while specialized embodied systems manage mid-level skills and low-frequency motor control. At the 2026 Zhiyuan Innovation Day, Yao unveiled the GO-3 Preview model, which uses a new WRAM architecture. The company plans to fully open-source the model by the end of 2026.
From Chinese robotics — Robot learning research
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 13.4 percent · Basis not reported · Reported zero-shot result; the excerpt does not specify an evaluation protocol. · Differing source assertions
“2026智元创新日具身作业生产力分论坛公布的数据显示，在训练数据规模扩展实验中，GO-3 Preview在20类技能100个任务上的Zero-Shot（零样本）平均成功率由13.4%提升至56.4%；在模型规模扩展实验中，零样本成功率由56.2%提升至73.2%。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 56.4 percent · Basis not reported · Reported zero-shot result; the excerpt does not specify an evaluation protocol. · Differing source assertions
“2026智元创新日具身作业生产力分论坛公布的数据显示，在训练数据规模扩展实验中，GO-3 Preview在20类技能100个任务上的Zero-Shot（零样本）平均成功率由13.4%提升至56.4%；在模型规模扩展实验中，零样本成功率由56.2%提升至73.2%。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 56.2 percent · Basis not reported · Reported zero-shot result; the excerpt does not specify an evaluation protocol. · Differing source assertions
“2026智元创新日具身作业生产力分论坛公布的数据显示，在训练数据规模扩展实验中，GO-3 Preview在20类技能100个任务上的Zero-Shot（零样本）平均成功率由13.4%提升至56.4%；在模型规模扩展实验中，零样本成功率由56.2%提升至73.2%。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 73.2 percent · Basis not reported · Reported zero-shot result; the excerpt does not specify an evaluation protocol. · Differing source assertions
“2026智元创新日具身作业生产力分论坛公布的数据显示，在训练数据规模扩展实验中，GO-3 Preview在20类技能100个任务上的Zero-Shot（零样本）平均成功率由13.4%提升至56.4%；在模型规模扩展实验中，零样本成功率由56.2%提升至73.2%。”
Exact source · revision 2Source owner not reported
Reported quantity · task_duration: 1 hours · Basis not reported
“人类几十秒到一分钟就能完成的物理操作，通用大模型可能需要耗费1—2小时，同时消耗海量Token，这根本无法满足真实产线的节拍要求。”
Exact source · revision 2Source owner not reported
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Robot learning researchSignalZhiyuan's Yao Maoqing: Embodied AI Will Adopt a Layered Architecture as General Models Struggle with Physical Tasks
Yao Maoqing, co-founder and president of Zhiyuan, stated that general-purpose large models lack the efficiency and low-level physical control required for real-world robotics. He proposed a layered architecture where general models handle high-level planning, while specialized embodied systems manage mid-level skills and low-frequency motor control. At the 2026 Zhiyuan Innovation Day, Yao unveiled the GO-3 Preview model, which uses a new WRAM architecture. The company plans to fully open-source the model by the end of 2026.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).