Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning
cs.RO, cs.AI, cs.LG
Submitted: 2026-09-03
Updated: 2026-09-19
Comments: 5 pages, 4 figures, 2 tables. Accepted to the IROS 2026 Workshop on Physical World Models for Scaling Embodied AI (PWMS 2026)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Sensorimotor World Models: Perception for Action via Inverse Dynamics
- Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding
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