# PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies

arXiv: https://arxiv.org/abs/2608.30378 · HTML: https://mlsanity.com/paper/2608.30378/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World model-based VLA, one of 13 directions in Vision-language-action models.
- Builds on 35 of its 36 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Placed in

- Vision-language-action models / [World model-based VLA](https://mlsanity.com/vla/world-model-based-vla/)

## Builds on (most cited first, 30 of 35)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Double/Debiased Machine Learning for Treatment and Causal Parameters](https://mlsanity.com/paper/1608.00060/) (2016)
- [JEPA-VLA: Video Predictive Embedding is Needed for VLA Models](https://mlsanity.com/paper/2602.11832/) (2026)
- [InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization](https://mlsanity.com/paper/2607.04988/) (2026)
- [JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling](https://mlsanity.com/paper/2608.09381/) (2026)
- [World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems](https://mlsanity.com/paper/2604.14732/) (2026)
- [ARM: Advantage Reward Modeling for Long-Horizon Manipulation](https://mlsanity.com/paper/2604.03037/) (2026)
- [VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulation](https://mlsanity.com/paper/2508.01622/) (2025)
- [LoLA: Long Horizon Latent Action Learning for General Robot Manipulation](https://mlsanity.com/paper/2512.20166/) (2025)
- [OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation](https://mlsanity.com/paper/2604.17876/) (2026)
- [FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization](https://mlsanity.com/paper/2606.05468/) (2026)
- [Vision Pretraining for Dense Spatial Perception](https://mlsanity.com/paper/2607.05247/) (2026)

## Abstract (arXiv)

Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: their representations are not explicitly required to describe how the scene evolves over multiple time scales, and deployment trajectories of unequal quality are often reused without separating useful dynamics from undesirable behavior. We introduce method, a direct world-action policy that combines outcome-agnostic predictive learning with outcome-aware policy improvement. method first retains a local fixed-offset JEPA objective and adds trajectory-relative multi-horizon transition alignment at 25%, 50%, 75%, and 100% of the remaining episode. These training-only targets require the current policy representation to preserve both local physical changes and longer-range task progress, without supplying explicit future tokens to the action head. method then trains an independent distributional value critic on cumulative deployment trajectories, computes action-chunk-aligned N-step advantages, and converts them into positive, negative, or null text conditions for a flow-matching actor. Thus, every valid trajectory can teach what physically happened, while the actor is deployed only under the condition associated with relatively better actions. The multi-horizon predictor and critic are removed from online execution, preserving direct action generation from the current observation, language instruction, and proprioception. redclaimAcross the three simulation benchmarks, method achieves the strongest overall performance while preserving the direct actor's online execution path.