Beyond One-Step Accuracy: State-Affine Latent Transition for Reliable Visual Planning
cs.RO, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/deepmindby/SALT
Terminology
Sources
- Combating the Compounding-Error Problem with a Multi-step Model
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Sensorimotor World Models: Perception for Action via Inverse Dynamics
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- DeepMind Control Suite
- Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models
- QQWorld: Quantile-Quantile Matching for World Model Regularization
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