PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
cs.RO, cs.AI
Submitted: 2026-08-31
Updated: 2026-09-18
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- Vision Pretraining for Dense Spatial Perception
- OpenVLA: An Open-Source Vision-Language-Action Model
- JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
- Flow Matching for Generative Modeling
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- JEPA-WAM: Stage-Level Joint-Embedding Prediction for World-Action Models in Robot Manipulation
- Being-H0.7: A Latent World-Action Model from Egocentric Videos
- JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
- V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
- DINOv2: Learning Robust Visual Features without Supervision
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
- FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization
- RedFlow: Redirect Failure into Action-level Corrections for Flow-matching VLA Policy
- Qwen2.5 Technical Report
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