Core Insights - The article discusses the introduction of GEN-0, a new type of embodied foundational model designed for multimodal training based on high-fidelity physical interactions, which aims to enhance robotic intelligence through real-world data [5][9]. Group 1: Model Characteristics - GEN-0 has been developed to capture human-level reflexes and physical common sense, featuring a core characteristic called "harmonic reasoning" that allows seamless training of thinking and action [5]. - The model has surpassed the critical threshold of 7 billion parameters, showing a phase transition where smaller models become stagnant while larger models continue to improve [6][11]. - GEN-0 demonstrates a strong scaling law, indicating that increased pre-training data and computational power predictably enhance the model's performance across multiple tasks [6][11]. Group 2: Data Utilization - The model is pre-trained on over 270,000 hours of real-world heterogeneous manipulation data, with the dataset expanding at a rate of over 10,000 hours per week [22]. - The data collection comes from diverse operational scenarios across thousands of households, warehouses, and workplaces, aiming to cover all conceivable operational tasks [24]. Group 3: Implications for Robotics - GEN-0 signifies a new era in embodied foundational models, where capabilities will grow predictably with real physical interaction data rather than relying solely on text, images, or simulated data [9]. - The findings highlight that smaller models struggle to process complex sensory-motor data during pre-training, while models with over 70 billion parameters can internalize large-scale pre-training data and quickly adapt to downstream tasks with minimal fine-tuning [15][11].

点击下方 卡片 ，关注" 具身智能 之心 "公众号 编辑丨具身智能之心 本文只做学术分享，如有侵权，联系删文 论文链接：https://arxiv.org/abs/2511.01331 论文名称：RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models 当下的痛点 RobustVLA的设计逻辑 鉴于在线强化学习交互过程中存在环境不确定性，这里考虑了观测噪声（传感器/摄像头故障）和动作噪声（高斯执行误差）及其联合效应。此外，基于这三个 方面开展了鲁棒性理论分析，确立了误差放大界限、回报漂移控制以及鲁棒稳定性保证。最后，我们推导出了正则化优化目标，包括模型雅可比矩阵正则化和动 作平滑正则化，以及鲁棒强化学习后训练目标。 视觉-语言-动作模型借助大规模多模态预训练，在机器人操作任务中展现出强大通用性，但在分布外场景中泛化能力受限。 分布外场景的核心挑战来自环境扰动，主要分为两类：观测扰动（传感器噪声、图像偏移、旋转、遮挡等）和动作扰动（执行器误差、高斯噪声等）。 现有强化学习后训练方法聚焦奖励最 ...

点击下方 卡片 ，关注" 具身智能 之心 "公众号 >>直播和内容获取转到 → 具身智能之心知识星球 点击按钮预约直播 都说具身智能领域高质量数据难寻也难求，背后的原因都绕不开一个核心： 采集困难 ！ 这不仅仅是每位具身从业者面临" 高质量具身数据 "获取难题，更是关于" 人如何教会机器理解世界 "的领域持续探索。 从遥操作（Teleoperation）作为核心数据来源的必然性，到动捕（Motion Capture）系统在精度与自由度间的艰难平衡；从ALOHA等 标杆项目揭示的端到端数据闭环范式，到互联网视频、合成数据（Synthetic Data）与真实机器人数据如何构建金字塔式的融合框 架；再到人机交互（HRI）设计中的延迟、眩晕与意图识别等终极难题，在面对成本和质量的考量之时，每种方式都有自己的"拦路 虎"与"杀手锏"。 本期 具身智能之心 "圆桌正当时"将联合 BV 百度风投副总裁崔轲迪 ，和5位具身领域青年科学家与创业者，一起剖析 具身智能数据 采集的底层逻辑、技术瓶颈与创新解法 ，具体将会从 采什么、为什么采、再到怎么采，采集方式是否有"高下之分"，如何大规模 采，全方位解构！ 期望本期圆桌能为正 ...

点击下方 卡片 ，关注" 具身智能 之心 "公众号 编辑丨具身智能之心 本文只做学术分享，如有侵权，联系删文 >> 点击进入→ 具身智能之心 技术交流群 最近在为大家收敛具身科研的几个重点模块：行业内容、本体形态、算法、还有部署的一些方案，已经汇总在 我们的社区内部。 目前为大家梳理了行业正在从事具身大脑、本体研发的公司（突然发现本体也卷不太动了......)，以及一些比较 活跃的具身实验室。方便大家判断和升学，除此之外，还有很多行业的研报，供大家判断具身的发展与周期。 本体方面，推荐几款适合科研的产品：SO-100系列、openarm系列、XLerobot系列等； SO100及升级版本，能上一些VA和VLA的算法，常见功能可以实现了； Openarm是一款双臂任务框架，目前有几家公司开始生产相关本体，缺乏移动能力，一些叠衣服、pick and place也都能满足。 XLerobot存在一定的移动能力，但不多，适合一些入门科研&个人开发使用，可以适配移动操作的一些任务。 其它开发平台，成本较高，需要一定的资金投入，可以参考方舟无限、星海图、宇树的几款本体。 算法层面，目前我们收拢了关于vla（训练、无需训练 ...

Core Insights - The "ZhiXing Plan - Overseas Recruitment" is a strategic talent recruitment initiative by the Beijing Academy of Artificial Intelligence aimed at attracting and nurturing high-level AI research talent from around the world [2]. Group 1: Program Overview - The "ZhiXing Plan" targets top graduates from global universities, inviting selected candidates for a research visit of six months or more at the Beijing Academy of Artificial Intelligence [2]. - Successful candidates will collaborate with leading international research teams on cutting-edge topics and gain entry into the ZhiYuan talent ecosystem [2]. Group 2: Recruitment Highlights - Exceptional performers during the visit may receive priority for full-time positions at the research institute, including roles such as Principal Investigator (PI), researcher, or postdoctoral fellow [5]. - The program offers access to advanced research topics and supercomputing resources, allowing collaboration with leading researchers in the field [5]. Group 3: Support and Resources - Participants will benefit from long-term academic development and resource support, including entry into the ZhiYuan academic network for ongoing research collaboration and career opportunities [7]. - Comprehensive support services will be provided, including academic mentorship and administrative assistance for both research and daily life [7][8]. Group 4: Target Audience and Research Areas - The recruitment is aimed at Chinese doctoral candidates, postdoctoral researchers, and formal research staff from top universities and laboratories [9]. - Research directions include brain-like models, intelligent systems, embodied intelligence, multimodal AI, and AI for Science, with candidates expected to have published at least three first-author papers in top conferences [9]. Group 5: Application Process - Applications are accepted year-round with rolling reviews until positions are filled [11]. - The process includes academic evaluation, interviews, and formal invitations for successful candidates [10]. Group 6: Vision and Goals - The "ZhiXing Plan - Overseas Recruitment" is positioned as a starting point for integrating into China's leading AI research platform, aiming to conduct globally impactful research and build long-term collaborative relationships [12].

作者丨 机器之心 点击下方 卡片 ，关注" 具身智能之心 "公众号 >> 点击进入→ 具身 智能之心 技术交流群 更多干货，欢迎加入国内首个具身智能全栈学习社区 ： 具身智能之心知识星球 (戳我) ， 这里包含所有你想要的。 要投 ICML 2026 顶会的小伙伴需要注意了，论文征集有了新规，包括但不限于： | ICML 2026 征稿新规 | | --- | ICML 2026 将于 2026 年 7 月 7 日至 12 日在韩国首尔举办，届时所有论文将采用双盲审稿机制，最终被录用的论文将在大会上进行展示。 投稿须以单个文件形式提交，具体要求如下： 论文被接收的作者可选择是否参会； 已接收论文的原始提交版本将被公开； 互审论文的数量有了限制。 正文部分最多 8 页； 注：论文被录用后，作者可在最终版本中为正文部分额外增加 1 页。 政策变更：论文被接收后，作者可选择是否参会 在论文录用通知发出后，作者需在指定日期前决定：是否选择亲自到会现场进行报告，或仅将论文收录至会议论文集（不进行现场展示）。 无论作者选择哪种方式，所有被录用的论文在论文集中的待遇完全相同，这些论文都将有资格参与 ICML 奖项评选。 对 ...

Core Viewpoint - Imeta-Y1 is a lightweight, cost-effective robotic arm designed specifically for beginners and researchers in the field of embodied intelligence, enabling low-cost and efficient algorithm validation and project development [2][5]. Group 1: Product Features - The robotic arm offers a complete open-source toolchain and code examples, facilitating a seamless process from data collection to model deployment [3][17]. - It supports dual-language interfaces (Python/C++) to cater to users' programming preferences, ensuring quick onboarding [3][18]. - Compatibility with ROS1 and ROS2 is provided, along with URDF models for smooth transitions between simulation and real-world applications [3][19]. - The arm features high-precision motion control, low power consumption, and an open hardware architecture, allowing for seamless integration from simulation to real machine [5][35]. Group 2: Technical Specifications - The robotic arm has a weight of 4.2 kg, a rated load of 3 kg, and 6 degrees of freedom, with a working radius of 612.5 mm and a repeat positioning accuracy of ±0.1 mm [8][19]. - It operates at a supply voltage of 24V and communicates via CAN, with external interfaces for power and CAN connections [8][19]. - The arm's joint motion range and maximum speeds are specified, ensuring versatility in various applications [8][19]. Group 3: Development and Support - A comprehensive open-source SDK is provided, including drivers, API interfaces, sample code, and documentation, supporting rapid application development [26][29]. - The product supports multi-modal data fusion, compatible with mainstream frameworks like TensorFlow and PyTorch, enabling end-to-end intelligent algorithm implementation [29][32]. - The company offers 24-hour rapid response for after-sales support, ensuring users receive timely assistance [3][19]. Group 4: Testing and Reliability - Rigorous hardware testing processes, including precision calibration, durability, load performance, and stability verification, ensure the robotic arm's reliability and safety across various application scenarios [35][39].

更多干货，欢迎加入国内首个具身智能全栈学习社区 ： 具身智能之心知识星球 (戳我) ， 这里包含所有 你想要的。 点击下方 卡片 ，关注" 具身智能之心 "公众号 作者丨具身智能之心 >> 点击进入→ 具身智能之心 技术交流群 马斯克的万亿元薪酬获批了，几个小时前，特斯拉股东释放埃隆:批准1万亿美元的薪酬方案，并授 权75%！ Annual Shareho Meeting Meeting 2025 l 本文只做学术分享，如有侵权，联系删文 I NAVA VA 017 . of and on 11 20 C 4-11 全场沸腾，"埃隆！埃隆！"的欢呼声回荡在整个会场。按照约定，马斯克必须达成12项雄心勃勃的 里程碑：市值目标、营收指标、盈利基准。也许，在不久，他将成为地球首位万亿富翁。 更多产业信息，欢迎加入具身智能之心知识星球获取，国内最大的具身全栈社区，和近2000名同 学，200家具身公司与机构一起交流产业、学术、工程落地等。 双十一优惠已经开启，欢迎新同学扫 码加入！ ...

Core Insights - The article discusses the development of DexNDM, a new method aimed at solving the sim-to-real challenge in dexterous robotic manipulation, particularly in achieving stable in-hand rotation of various objects [2][5][31] Group 1: Background and Challenges - High dexterity in remote operation of complex tools, such as using a screwdriver or hammer, has been a long-standing challenge in robotics [4] - Traditional direct mapping remote operation methods are limited to simple tasks and cannot handle complex manipulations requiring fine motor skills [4] Group 2: DexNDM Methodology - DexNDM proposes a semi-autonomous remote operation paradigm that breaks down complex tasks into stable, reliable atomic skills that robots can execute autonomously [5] - The method focuses on learning general, stable atomic skills for in-hand object rotation, covering a wide range of scenarios including challenging elongated and small objects [5][14] Group 3: Key Features and Achievements - DexNDM achieves unprecedented dexterity by enabling continuous rotation of elongated objects and intricate manipulation of small objects under challenging wrist postures [7][14] - The method demonstrates superior performance in manipulating complex geometries compared to previous works, even with more general hardware [14] - It showcases high adaptability to various wrist postures and rotation axes, allowing for precise control regardless of the mechanical hand's orientation [17] Group 4: Robustness and Practical Applications - The DexNDM system exhibits high dexterity and robustness, successfully performing complex tool usage tasks such as tightening screws and assembling furniture [21] - The system's robustness allows it to handle long-horizon assembly tasks without interruption, even in the presence of unforeseen scenarios [21] Group 5: Innovations in Data Collection and Modeling - DexNDM employs a joint-wise neural dynamics model that effectively fits real-world data to bridge the gap between simulation and reality [24] - An automated data collection strategy, termed "chaos box," is utilized to gather diverse interaction data with minimal human intervention [28] - The training of a residual policy network is implemented to compensate for the dynamics gap between simulation and real-world applications [30]

Group 1 - The core promotion period for the embodied intelligence series is from November 1 to November 11 [2] - Discounts include 30% off for new users and 50% off for renewals [3] - The embodied intelligence series courses are available at a price of 8 BT for a single course and 7 BT for three courses [2] Group 2 - Additional benefits include significant discounts on robotic arms and development components [3] - The company encourages inquiries for more details about the promotional activities [1][3]