# JEPA-WAM: Connecting Generated Visual Instructions to World Action Models through JEPA Latent Representations

arXiv: https://arxiv.org/abs/2609.20277 · HTML: https://mlsanity.com/paper/2609.20277/

## 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 15 of its 22 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 15 of 15)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Video Generators are Robot Policies](https://mlsanity.com/paper/2508.00795/) (2025)
- [Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions](https://mlsanity.com/paper/2505.02152/) (2025)
- [When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs](https://mlsanity.com/paper/2602.17659/) (2026)
- [DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation](https://mlsanity.com/paper/2607.04927/) (2026)
- [APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies](https://mlsanity.com/paper/2606.12366/) (2026)
- [DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing](https://mlsanity.com/paper/2603.28713/) (2026)
- [Latent Video Prediction Learns Better World Models](https://mlsanity.com/paper/2605.15618/) (2026)

## Abstract (arXiv)

World Action Models (WAMs) have demonstrated strong robotic manipulation capabilities by augmenting pretrained video generative models with action experts. However, current WAMs still show limited instruction-following ability when conditioned solely on text instructions. We argue that this limitation stems in part from a structural imbalance in robot-learning data: rich visual-action trajectories are often paired with sparse and repetitive language annotations, allowing policies to identify tasks from visual context and motion regularities rather than grounding the instruction itself. To address this limitation, we introduce JEPA-WAM, which augments each text instruction with a bank of stochastically generated visual instructions, providing diverse visual cues for instruction following. Specifically, JEPA-WAM uses an off-the-shelf text-to-image generator to sample multiple task-completion images conditioned on the text instruction, without training the generator. Although these generated images may differ from the current visual scene in appearance and layout, they remain semantically aligned with the instruction and serve as visual goal references. To focus on task-level semantics beyond appearance, we encode these references with a frozen V-JEPA 2.1 encoder. The resulting dense goal representations are compressed into compact goal tokens that condition both the video and action experts through cross-attention. We further construct a real-robot instruction-following benchmark covering in-distribution, out-of-distribution scene, and out-of-distribution instruction settings. On this benchmark, JEPA-WAM achieves success rates of 87.3%, 74.5%, and 80.9% in these three settings, outperforming π0 and Fast-WAM by at least 10.0, 27.3, and 14.5 percentage points, respectively.