Gaode Releases First Full-Body Base Model λ0 Based on Open-World Behavior
Overview
Gaode, under the Alibaba Group, officially released its first full-body base model λ0 based on open-world behavior. This model enables robots to learn full-body coordination, including movement, posture, and hand operations, solely through human action data, thus overcoming the limitations of 'local action learning.' In the SIMPLE simulation benchmark and multiple real-world evaluations, λ0 achieved state-of-the-art performance, with data collection efficiency approximately 3.4 times that of mainstream methods and a 22.5% increase in real-world task success rate compared to the strongest baseline.
From QbitAI — Robotics
Event evidence and corrections
1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · data_collection_efficiency: 3.4 other · Basis not reported
“在SIMPLE仿真基准及多项真机评测中，λ0均取得SOTA表现，数据采集效率约为主流方法的3.4倍，真机任务成功率较最强对比基线提升22.5%。”
Exact source · revision 2qbitai
Reported quantity · Reported success rate: 22.5 percent · Basis not reported
“在SIMPLE仿真基准及多项真机评测中，λ0均取得SOTA表现，数据采集效率约为主流方法的3.4倍，真机任务成功率较最强对比基线提升22.5%。”
Exact source · revision 2qbitai
Reported quantity · single_demo_collection_time: 29 other · Basis not reported
“与机器人本体采集相比，该方式将代表性任务的单条示范采集用时由约100秒缩短至29秒，采集效率约为原来的3.4倍。”
Exact source · revision 2qbitai
Reported quantity · data_collection_efficiency_comparison: 3.4 other · Basis not reported
“与机器人本体采集相比，该方式将代表性任务的单条示范采集用时由约100秒缩短至29秒，采集效率约为原来的3.4倍。”
Exact source · revision 2qbitai
Reported quantity · data_set_size: 500 hours · Basis not reported
“基于这一可规模化的管线，高德构建了包含500小时开放世界无本体全身数据的HumanVerse-500数据集。”
Exact source · revision 2qbitai
Artifact availability · dataset: available
“附 项目主页：https://lambdahumanoid.github.io/ 技术报告：https://arxiv.org/abs/2610.18950 GitHub：https://github.com/LambdaHumanoid/openlambda HumanVerse 数据样例：https://huggingface.co/datasets/lambda-humanoid/HumanVerse-500-sample 本文由高德提供，量子位获授权转载，观点归原作者所有。”
Exact source · revision 2qbitai
Artifact availability · paper: available
“附 项目主页：https://lambdahumanoid.github.io/ 技术报告：https://arxiv.org/abs/2610.18950 GitHub：https://github.com/LambdaHumanoid/openlambda HumanVerse 数据样例：https://huggingface.co/datasets/lambda-humanoid/HumanVerse-500-sample 本文由高德提供，量子位获授权转载，观点归原作者所有。”
Exact source · revision 2qbitai
Evidence dependency changes (2)
- 2026-10-30T20:20:20.543Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T20:20:04.114Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- QbitAI — RoboticsSignalGaode Releases First Full-Body Base Model λ0 Based on Open-World Behavior
Gaode, under the Alibaba Group, officially released its first full-body base model λ0 based on open-world behavior. This model enables robots to learn full-body coordination, including movement, posture, and hand operations, solely through human action data, thus overcoming the limitations of 'local action learning.' In the SIMPLE simulation benchmark and multiple real-world evaluations, λ0 achieved state-of-the-art performance, with data collection efficiency approximately 3.4 times that of mainstream methods and a 22.5% increase in real-world task success rate compared to the strongest baseline.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).