Juno: Taming Predictive Latents for Vision-Language-Action Models
cs.RO, cs.CV
Submitted: 2026-10-07
Updated: 2026-10-11
Project page: https://juno-policy.github.io/ABSTRACT
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Revisiting Feature Prediction for Learning Visual Representations from Video
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- WorldVLA: Towards Autoregressive Action World Model
- LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
- WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
- Self-Supervised Policy Adaptation during Deployment
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
- H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
- RoboTTT: Context Scaling for Robot Policies
- OpenVLA: An Open-Source Vision-Language-Action Model
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- Evaluating Real-World Robot Manipulation Policies in Simulation
- Being-H0.7: A Latent World-Action Model from Egocentric Videos
- InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
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