Cross-Embodiment Robot Foundation World Models with Latent Actions
cs.RO
Submitted: 2026-10-07
Updated: 2026-10-07
Project page: https://lacwm.github.io
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
- AdaWorld: Learning Adaptable World Models with Latent Actions
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- GAIA-1: A Generative World Model for Autonomous Driving
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- DreamGen: Unlocking Generalization in Robot Learning through Video World Models
- Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
- CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Long-Context State-Space Video World Models
- GameFactory: Creating New Games with Generative Interactive Videos
- Matrix-Game: Interactive World Foundation Model
- Universal Actions for Enhanced Embodied Foundation Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving