DeltaWorld: Physically Consistent Interactive World Simulators via Action-Conditioned Latent Increment Learning
cs.RO
Submitted: 2026-10-02
Updated: 2026-10-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- Data Scaling Laws in Imitation Learning for Robotic Manipulation
- FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset
- AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation
- Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
- Interactive World Simulator for Robot Policy Training and Evaluation
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
- Large Video Planner Enables Generalizable Robot Control
- Mastering Diverse Domains through World Models
- Ctrl-World: A Controllable Generative World Model for Robot Manipulation
- RoboDreamer: Learning Compositional World Models for Robot Imagination
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- FeelWorld: Visuo-Tactile World Model for Hierarchical Contact Prediction and Planning
- WorldEval: World Model as Real-World Robot Policies Evaluator
- dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
- Learning Latent Dynamics for Planning from Pixels
- Dream to Control: Learning Behaviors by Latent Imagination
- Back to the Features: DINO as a Foundation for Video World Models
- Cosmos 3: Omnimodal World Models for Physical AI
- DreamGen: Unlocking Generalization in Robot Learning through Video World 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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies