SWAM: Scaling World Action Models with Cross-Modal Alignment
cs.CV, cs.RO
Submitted: 2026-11-09
Updated: 2026-11-11
Terminology
Sources
- HunyuanVideo 1.5 Technical Report
- Wan: Open and Advanced Large-Scale Video Generative Models
- Seedance 2.0: Advancing Video Generation for World Complexity
- World Action Models are Zero-shot Policies
- Causal World Modeling for Robot Control
- OpenWAM: An Open Framework for Composable World-Action Models
- Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?
- What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction
- Rethinking Representations for World-Action Modeling
- RoboPocket: Improve Robot Policies Instantly with Your Phone
- Video Prediction Policy 2: Predict Better, Act Better
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- OpenVLA: An Open-Source Vision-Language-Action Model
- EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
- EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
- Qwen3-VL Technical Report
- Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
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