Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China(清华大学交叉信息研究院);Department of Computer Science, Princeton University, New Jersey, US(普林斯顿大学计算机科学系);Galaxea Inc., Beijing, China(Galaxea公司)
Diffusion models and flow matching have become a cornerstone of robotic imitation learning, yet they suffer from a structural inefficiency where inference is often bound to a fixed integration schedule that is agnostic to state complexity. This paradigm forces the policy to expend the same computational budget on trivial motions as it does on complex tasks. We introduce Generative Control as Optimization (GeCO), a time-unconditional framework that transforms action synthesis from trajectory integration into iterative optimization. GeCO learns a stationary velocity field in the action-sequence space where expert behaviors form stable attractors. Consequently, test-time inference becomes an adaptive process that allocates computation based on convergence--exiting early for simple states while refining longer for difficult ones. Furthermore, this stationary geometry yields an intrinsic, training-free safety signal, as the field norm at the optimized action serves as a robust out-of-distribution (OOD) detector, remaining low for in-distribution states while significantly increasing for anomalies. We validate GeCO on standard simulation benchmarks and demonstrate seamless scaling to pi0-series Vision-Language-Action (VLA) models. As a plug-and-play replacement for standard flow-matching heads, GeCO improves success rates and efficiency with an optimization-native mechanism for safe deployment. Video and code can be found at https://hrh6666.github.io/GeCO/
Speech to Reality: On-Demand Production using Natural Language, 3D Generative AI, and Discrete Robotic Assembly
Computer Science and Artificial Intelligence Lab(计算机科学与人工智能实验室);Massachusetts Institute of Technology(麻省理工学院);Center for Bits and Atoms(比特与原子中心);Department of Mechanical Engineering(机械工程系)
Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation
Yonsei University(延世大学);University of California, Berkeley(加州大学伯克利分校);Samsung Research(三星研究院);Massachusetts Institute of Technology(麻省理工学院);Ewha Womans University(梨花女子大学)
Multi-modal perception for soft robotic interactions using generative models
The BioRobotics Institute, Sant’Anna School of Advanced Studies(圣安娜高级研究院生物机器人研究所);Sant’Anna School of Advanced Studies(圣安娜高级研究院);University College London(伦敦大学学院)
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)
The University of Hong Kong(香港大学);AgileX Robotics(极目机器人);Shanghai AI Laboratory(上海人工智能实验室);Shenzhen University(深圳大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models
Massachusetts Institute of Technology (MIT)(麻省理工学院);MIT(麻省理工学院);Google DeepMind(谷歌DeepMind);Google, Paradigms of Intelligence(谷歌、范式智能);Autodesk Research(Autodesk研究);MIT Mechanical Engineering(麻省理工学院机械工程系);MIT Architecture(麻省理工学院建筑系);MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)
Generative Artificial Intelligence in Robotic Manipulation: A Survey
LimX Dynamics(灵蜥科技);University of Hong Kong(香港大学);Southern University of Science and Technology(南方科技大学);Zhejiang University(浙江大学);The Hong Kong Polytechnic University(香港理工大学);The Hong Kong University of Science and Technology(香港科技大学);Tsinghua University(清华大学);Great Bay University(大湾区大学)
Mani-GPT: A Generative Model for Interactive Robotic Manipulation
Southern University of Science and Technology(南方科技大学);PLA General Hospital(中国人民解放军总医院);National Clinical Research Center for Orthopedics, Sports Medicine and Rehabilitation(国家骨科、运动医学与康复医学临床研究中心)
Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations
German Research Center for AI(德国人工智能研究中心);Nvidia(英伟达);Massachusetts Institute of Technology(麻省理工学院);New York University(纽约大学);Carnegie Mellon University(卡内基梅隆大学);Technische Universität Darmstadt(达姆施塔特工业大学);Georgia Institute of Technology(佐治亚理工学院)
Sim-to-Real Transfer via a Style-Identified Cycle Consistent Generative Adversarial Network: Zero-Shot Deployment on Robotic Manipulators through Visual Domain Adaptation
Institute for Research in Technology (IIT)(技术研究 institute);ICAI School of Engineering(工程学院);Comillas Pontifical University(宗座大学)
Making Physical Objects with Generative AI and Robotic Assembly: Considering Fabrication Constraints, Sustainability, Time, Functionality, and Accessibility
College of Engineering and Physical Sciences, Aston University(工程与物理科学学院,阿斯顿大学);Department of Computer Science Department, Loughborough University(计算机科学系,洛桑大学)
RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation
Xiaomi EV(小米电动车);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学 Gallagher人工智能学院);School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机科学与信息工程学院)
RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Massachusetts Institute of Technology(麻省理工学院);National University of Singapore(新加坡国立大学);NVIDIA(英伟达);MIT-IBM Watson AI Lab(麻省理工-IBM沃森人工智能实验室)