Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object. As robots attempt more demanding in-hand maneuvers, safety, such as not dropping the object, becomes critical, yet it is rarely measured. We study in-hand object pose reaching, a task that demands diverse and difficult grasps: moving an object to almost any position and orientation within reach of the fingers, at any wrist orientation, through long sequences of consecutive goals. We present a recipe for training such policies for a LEAP hand in simulation without human data, built on a range of insights, from diverse resets and goals via generated grasp datasets to an adaptive friction curriculum. With careful system identification, the policies transfer zero-shot to the real hand, using either motion capture or a single wrist-mounted depth camera, and prove remarkably capable and robust. On top of the task policy, we add a learned residual safety filter with adjustable conservativeness, letting us tune the balance between performance and safety and greatly reduce object drops. In 13.3 hours of real-robot evaluation over 4,800 unseen goals across 4 objects and diverse wrist orientations, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, and the filter cuts its drops by 75% while still reaching 91.5% of goals. The policies can also spin a lightbulb held in an arbitrary pose, reach out-of-distribution goals, withstand fast arm motion and perturbations, and, needing only a wrist camera, serve as portable skills such as screwing in a lightbulb. We release the full recipe as a platform for studying performance, reliability, and safety in high-dimensional dexterous systems. Videos and more are available at https://ian-chuang.github.io/dexsafe/.
Safe and Steerable Geometric Motion Policies for Robotic Dexterous Manipulation
Computer Science Department, Stanford University（斯坦福大学计算机科学系）；Laboratory of Signals and Systems, University of Paris-Saclay, CNRS, CentraleSupélec（巴黎-萨克雷大学信号实验室，CNRS，CentraleSupélec）；Toyota Research Institute（丰田研究院）
UniBiDex: A Unified Teleoperation Framework for Robotic Bimanual Dexterous Manipulation
Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）；Dongguan Key Laboratory of Intelligent Equipment and Smart Industry, School of Advanced Engineering, The Great Bay University（东莞智能装备与智能制造重点实验室，高级工程学院，大湾区大学）；Department of Mechanical Engineering, The Hong Kong Polytechnic University（香港理工大学机械工程系）；Guangdong Academy of Sciences（广东省科学院）
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
Institute for AI, Peking University（北京大学人工智能研究院）；Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心）；University College London（伦敦大学学院）；Carnegie Mellon University（卡内基梅隆大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
Stanford University（斯坦福大学）；Carnegie Mellon University（卡内基梅隆大学）；Georgia Tech（佐治亚理工学院）；Robotics at Google（谷歌机器人学（注：此处按机构含义直译，“Robotics at Google”通常译为“谷歌机器人学”，但严格按要求仅翻译机构名称本身，不加入额外信息））
SkillWeave: Weaving Heterogeneous Demonstrations into Long-Horizon Manipulation Skills
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人学院）；Keio University（庆应义塾大学）；College of Engineering, University of California, Berkeley（加州大学伯克利分校工程学院）；Bosch Center for Artificial Intelligence（博世人工智能中心）
A Learning-based Controller for Multi-Contact Grasps on Unknown Objects with a Dexterous Hand
DLR Institute of Robotics & Mechatronics（德国宇航中心机器人与机电一体化研究所）；Technical University of Munich（慕尼黑工业大学）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models
Google（谷歌）；Oxford University（牛津大学）；Harvard University（哈佛大学）；CMU（卡内基梅隆大学）；Cohere（Cohere公司）；UCL（伦敦大学学院）；University of Zurich（苏黎世大学）；MLCommons（机器学习通用组织）；Kaggle（Kaggle平台）
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
Siebel School of Computing（计算科学系）；Data Science, University of Illinois Urbana-Champaign（数据科学，伊利诺伊大学厄巴纳-香槟分校）；School of Business, Stevens Institute of Technology（商学院，史蒂文斯理工学院）
ClutterDexGrasp: A Sim-to-Real System for General Dexterous Grasping in Cluttered Scenes
CFCS, School of Computer Science, Peking University（计算机学院，北京大学）；PKU-AgiBot Lab（北京大学阿吉机器人实验室）；PKU-PsiBot Lab（北京大学Psi机器人实验室）；Princeton University（普林斯顿大学）
IndustryNav: Evaluating Spatial Reasoning and Safety of Embodied Agents in Dynamic Industrial Navigation
Michigan State University（密歇根州立大学）；Independent Researcher（独立研究者）；University of California, Irvine（加州大学尔湾分校）；Ohio State University（俄亥俄州立大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Santa Barbara（加州大学圣巴巴拉分校）；University of Pittsburgh（匹兹堡大学）；University of Virginia（弗吉尼亚大学）；Arizona State University（亚利桑那州立大学）；Purdue University Northwest（普渡大学西北分校）
