World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories
cs.RO, cs.CV
Submitted: 2026-10-01
Updated: 2026-10-01
Comments: Accepted at NeurIPS 2026 (Spotlight). Url: https://jiahuilei.com/projects/wmm/
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- MoFM: A Large-Scale Human Motion Foundation Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control
- BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
- OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation
- Causal Diffusion Transformers for Generative Modeling
- DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
- Scaling Cross-Embodiment World Models for Dexterous Manipulation
- Classifier-Free Diffusion Guidance
- Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies
- Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
- FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation
- Multimodal Diffusion Forcing for Forceful Manipulation
- Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation
- PHUMA: Physically Reliable Humanoid Locomotion Dataset
- LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
- World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
- Geometry-aware 4D Video Generation for Robot Manipulation
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