Cover Image

NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Hongyu, Sun, Lingfeng, Hu, Yafei, Ta, Duy, Barry, Jennifer, Konidaris, George, Fu, Jiahui
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning
by: Fu, Jiahui, et al.
Published: (2026)

Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis
by: Li, Dayou, et al.
Published: (2026)

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
by: Dharmarajan, Karthik, et al.
Published: (2025)

VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
by: Chen, Hanzhi, et al.
Published: (2025)

One-Shot Cross-Geometry Skill Transfer through Part Decomposition
by: Thompson, Skye, et al.
Published: (2026)

Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation
by: Xie, Senwei, et al.
Published: (2025)

FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation
by: Wang, Sen, et al.
Published: (2025)

KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV
by: Chen, Zhihao, et al.
Published: (2026)

SAGE: Bridging Semantic and Actionable Parts for GEneralizable Manipulation of Articulated Objects
by: Geng, Haoran, et al.
Published: (2023)

V-HOP: Visuo-Haptic 6D Object Pose Tracking
by: Li, Hongyu, et al.
Published: (2025)

Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation
by: Raychaudhuri, Sonia, et al.
Published: (2024)

Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
by: Quartey, Benedict, et al.
Published: (2026)

Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
by: Tsagkas, Nikolaos, et al.
Published: (2024)

RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation
by: Tang, Tutian, et al.
Published: (2023)

Dense Monocular Motion Segmentation Using Optical Flow and Pseudo Depth Map: A Zero-Shot Approach
by: Huang, Yuxiang, et al.
Published: (2024)

RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation
by: Kuang, Yuxuan, et al.
Published: (2024)

G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation
by: Chen, Tianxing, et al.
Published: (2024)

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation
by: Zeng, Huajian, et al.
Published: (2026)

DriveVA: Video Action Models are Zero-Shot Drivers
by: Liu, Mengmeng, et al.
Published: (2026)

Zero-shot Reconstruction of In-Scene Object Manipulation from Video
by: Lin, Dixuan, et al.
Published: (2025)

EmboAlign: Aligning Video Generation with Compositional Constraints for Zero-Shot Manipulation
by: Zhang, Gehao, et al.
Published: (2026)

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
by: Chen, Jiayi, et al.
Published: (2026)

FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
by: Guo, Jun, et al.
Published: (2025)

FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
by: Xi, Zichen, et al.
Published: (2026)

Zero-Shot Temporal Interaction Localization for Egocentric Videos
by: Zhang, Erhang, et al.
Published: (2025)

Improving Zero-Shot ObjectNav with Generative Communication
by: Dorbala, Vishnu Sashank, et al.
Published: (2024)

Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
by: He, Haoran, et al.
Published: (2024)

Towards Generative Predictive Display for Vision-Based Teleoperation: A Zero-Shot Benchmark of Off-the-Shelf Video Models
by: Khalil, Aws, et al.
Published: (2026)

FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects
by: Eisner, Ben, et al.
Published: (2022)

Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
by: Fan, Chenyou, et al.
Published: (2025)

SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting
by: Qureshi, Mohammad Nomaan, et al.
Published: (2024)

ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
by: Yan, Ge, et al.
Published: (2025)

DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation
by: Duisterhof, Bardienus P., et al.
Published: (2023)

FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following
by: Lin, Zijun, et al.
Published: (2025)

HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
by: Chen, Zerui, et al.
Published: (2026)

NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants
by: Qin, Yiran, et al.
Published: (2025)

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
by: Kim, Young Hun, et al.
Published: (2025)

ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos
by: Shi, Junyao, et al.
Published: (2025)

You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
by: Zhou, Huayi, et al.
Published: (2025)

SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
by: Sun, Xuefei, et al.
Published: (2026)