KinoGen: Customizable Humanoid Loco-Manipulation References via Kinematically Grounded Video Generation
cs.RO
Submitted: 2026-10-14
Updated: 2026-10-14
Project page: https://kinogen-humanoid.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
- From Generated Human Videos to Physically Plausible Robot Trajectories
- GRAIL: Generating Humanoid Loco-Manipulation from World Models
- GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training
- Morphology-Consistent Humanoid Interaction through Robot-Centric Video Synthesis
- UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots
- HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos
- Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
- ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
- Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
- Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors
- OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
- SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
- Robot-Factored World Models via Robot Rendering
- RoboEdit: Turning Human Manipulation Videos into Scalable Robot Experience
- Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video
- Grounding Generated Videos in Feasible Plans via World Models
- V-Dreamer: Automating Robotic Simulation and Trajectory Synthesis via Video Generation Priors
- Seedance 2.0: Advancing Video Generation for World Complexity
- TAPNext++: What's Next for Tracking Any Point (TAP)?
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies