Learning Transferable World-Action Models from Task-Paired Human Videos
cs.CV, cs.RO
Submitted: 2026-10-09
Updated: 2026-10-09
Project page: https://watch-wam.github.io
Sources
- Cosmos World Foundation Model Platform for Physical AI
- Wan: Open and Advanced Large-Scale Video Generative Models
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- World Action Models are Zero-shot Policies
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
- MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos
- Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time
- EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
- EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
- Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
- Cosmos 3: Omnimodal World Models for Physical AI
- HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation
- Emergence of Human to Robot Transfer in Vision-Language-Action Models
- In-Context Imitation Learning via Next-Token Prediction
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