EVEWorld: Physical Evolution Supervision for Embodied World Models
cs.CV
Submitted: 2026-10-02
Updated: 2026-10-02
Comments: 44 pages
Code: https://github.com/behappya/EVEWorld
Project page: https://behappya.github.io/EVEWorld
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- Qwen3-VL Technical Report
- Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
- ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
- Rethinking Video Generation Model for the Embodied World
- SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
- DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
- LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- Gemini: A Family of Highly Capable Multimodal Models
- GigaWorld-0: World Models as Data Engine to Empower Embodied AI
- GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation
- Classifier-Free Diffusion Guidance
- EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
- RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- A Comprehensive Survey on World Models for Embodied AI
- WorldEval: World Model as Real-World Robot Policies Evaluator
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