Where Predictive Supervision Goes Shapes What VLA Policies Learn
cs.RO, cs.AI
Submitted: 2026-09-29
Updated: 2026-10-01
Comments: 38 pages (9 pages main text + appendix), 13 figures, 21 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
- GLaD: Geometric Latent Distillation for Vision-Language-Action Models
- Video Representation Learning by Dense Predictive Coding
- DINO-Foresight: Looking into the Future with DINO
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation
- Unified Vision-Language-Action Model
- FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
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