From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models
cs.CV, cs.RO
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/showlab/MetaWAM
Terminology
Sources
- World Action Models: The Next Frontier in Embodied AI
- World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- World Action Models are Zero-shot Policies
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- DreamGen: Unlocking Generalization in Robot Learning through Video World Models
- Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
- Unified Video Action Model
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- GigaWorld-Policy: An Efficient Action-Centered World--Action Model
- Latent Action Pretraining from Videos
- Latent Action Pretraining Through World Modeling
- VQ-ACE: Efficient Policy Search for Dexterous Robotic Manipulation via Action Chunking Embedding
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- Wavelet-Based Image Tokenizer for Vision Transformers
- Cosmos World Foundation Model Platform for Physical AI
- Wan: Open and Advanced Large-Scale Video Generative Models
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs