# Achieve What You Imagined: Learning to Align Actions with Visual Plans

arXiv: https://arxiv.org/abs/2609.33832 · HTML: https://mlsanity.com/paper/2609.33832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 6 of 6)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies](https://mlsanity.com/paper/2606.15768/) (2026)
- [Turning Video Models into Generalist Robot Policies](https://mlsanity.com/paper/2605.27817/) (2026)

## Abstract (arXiv)

World-action models can jointly predict future visual observations and robot actions. However, discrepancies may exist between their visual predictions and the consequences implied by generated actions. We observe that WAMs can often generate visually plausible task-completion outcomes before producing action sequences that reliably achieve them. Consequently, we treat the WAM-generated visual prediction as a goal-conditioned visual proposal rather than a directly executable plan. We use a frozen action-conditioned world model to predict action-conditioned consequences and construct feedback based on consistency between the two future predictions and alignment with the terminal goal. Leveraging this feedback, we employ Flow Policy Optimization (FPO) to optimize the action head of the WAM. This framework avoids online robot interaction and additional training of task-specific reward models. Across four real-world UR5 manipulation tasks, our method increases the mean success rate from 43.4% to 75.1%, compared with 61.4% for π0.5. These results show that cross-model prediction discrepancy can provide useful feedback for improving robot policies under the evaluated manipulation tasks. Website: https://imagine-to-achieve.github.io/