KineWorld: Action-Induced Transport Fields for Embodied World Modeling
cs.CV, cs.RO
Submitted: 2026-10-05
Updated: 2026-10-08
Comments: 36 pages. Project page and code: https://modaxiansheng.github.io/KineWorld/
Project page: https://modaxiansheng.github.io/KineWorld
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Motus: A Unified Latent Action World Model
- BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
- BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
- DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
- Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control
- Vidar: Embodied Video Diffusion Model for Generalist Manipulation
- GigaWorld-0: World Models as Data Engine to Empower Embodied AI
- Ctrl-World: A Controllable Generative World Model for Robot Manipulation
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
- Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
- CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
- RealWonder: Real-Time Physical Action-Conditioned Video Generation
- GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation
- WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
- Wan: Open and Advanced Large-Scale Video Generative Models
- Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
- PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
- RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models