AITOPAI热报
ModelsMulti-source87°

NVIDIA 发布开源机器人基础模型 GR00T 2，端到端完成化学实验

Official accountJim Fan@jimfan
Post· 11 sources
View the post
Why we picked it

NVIDIA 把机器人开发全链路都开源了：模型权重、10 万小时数据、仿真引擎、硬件设计全给。演示里 GR00T 2 真手做化学实验还是 1 倍速无剪辑。搞具身智能的团队真该去看看，省多少从头造轮子的功夫。

NVIDIA 研究副总裁 Jim Fan 发布 GR00T 2，这是其最新的开源机器人 System One 模型，全部权重开放下载，且可完全运行在机器人本体计算上，无需外部连接。演示视频中，GR00T 2 以 1 倍原速控制真实灵巧手，自主完成一个化学实验并自行清理，全程无剪辑。

Image · Jim Fan
Body

模型支持长程任务：将灵巧操作与全身控制串联成 20+ 步、时长 5 分钟以上的连续动作，例如完整执行化学实验或组装航模。其 X-Adapt 机制可从人类可穿戴设备和仿真等易获取数据源学习，再零样本迁移到多种真实机器人。此外模型原生集成前沿智能体，用于物理推理、错误恢复和安全监控。

开源范围覆盖模型权重、X-Adapt 配方（12 月上线）、智能体框架、仿真引擎、标注引擎、硬件设计以及 10 万小时（约 11 年经验）训练数据。相比多数厂商只开放权重，NVIDIA 把整条开发链全部公开，可能显著降低具身智能的入门门槛，开发者与硬件团队可直接基于这套栈搭建自己的机器人。

Original · Jim Fan

Autonomous, uncut, 1x speed. This is GR00T 2 controlling real dexterous hands to perform a chemistry lab experiment (and clean up after itself) end to end. Episode 1 of a new series! I’ll keep dropping real-time robot videos, with none of the “4x” or “8x” labels you usually see in the corner. No one can speed up reality, except Dr. Strange ;)

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include GR00T 2, NVIDIA, 具身智能, 开源模型.

Source attribution: curated from Jim Fan (@jimfan). Cross-source corroboration: 11 independent sources have covered this development (including Decoder, Thomas Wolf, pandaily), confirming industry-wide signal strength.

#GR00T 2#NVIDIA#具身智能#开源模型#机器人

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-source03:02
Chinese contentNvidia 发布 GR00T 2：从视频学习人类动作来训练机器人

Nvidia 这次把机器人训练的数据来源换成了 40 万小时人类视频，不用人工遥操作逐个示范了。不过成功率从 10% 到 80% 不等，离稳定可用还有距离。做机器人或具身智能的团队值得对比一下自家数据管线，看看视频学习路线能不能省成本。

#GR00T 2#Nvidia#机器人#具身智能
Event
Official accountDecoder@Maximilian SchreinerSource
ModelsBuildersSelected23:35
Runway releases Praxis-1 robot model with open weights

An open-weights, Apache 2.0 robot control model removes the licensing barriers that usually come with robotics foundation models, letting teams self-host and modify freely. Robotics engineers and embodied-AI researchers can fine-tune Praxis-1 on their own hardware instead of licensing closed systems. Compared with closed offerings from rivals such as Physical Intelligence, this gives startups a low-cost starting point for building real-world robot behaviour.

#Runway#Praxis-1#open-source models#robotics
Official accountRunway ML@runwaymlSource
ModelsUS vs ChinaMulti-source23:33
Chinese contentRunway 发布 Praxis-1，速度比 GPT-6 Astra 快 15.6 倍、成本低 51 倍

Runway 把自家机器人模型 Praxis-1 和 GPT-6 Astra 放在同一个工作站上比，结果快了 15.6 倍，每个任务还便宜 51 倍。做机器人或自动化的开发者可以关注这种专用模型和通用 LLM 的选型对比。

#Praxis-1#Runway#GPT-6 Astra#具身智能
Event
Official accountRunway ML@runwaymlSource
ModelsBuildersMulti-sourceSelected23:30
DeepMind releases AlphaGenome 2 DNA model with doubled variant detection

The move from tissue-level averages to single-cell-type resolution changes what genetics labs can do with variant interpretation: rare-disease teams can now pinpoint which specific cell type a variant disrupts rather than relying on broad tissue signals. Computational biologists and genomics researchers can start testing it immediately via the free AlphaGenome API for non-commercial work. Compared with prior variant-effect predictors, the conditional architecture and cross-modal imputation reduce the need to run every assay before planning follow-up experiments.

#DeepMind#AlphaGenome#genomics#AI for science
Event
IT之家Source