# XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation

arXiv: https://arxiv.org/abs/2610.03516 · HTML: https://mlsanity.com/paper/2610.03516/

## 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 33 of its 37 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

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

## Builds on (most cited first, 30 of 33)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation](https://mlsanity.com/paper/2402.08191/) (2024)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [TesserAct: Learning 4D Embodied World Models](https://mlsanity.com/paper/2504.20995/) (2025)
- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [Prediction with Action: Visual Policy Learning via Joint Denoising Process](https://mlsanity.com/paper/2411.18179/) (2024)
- [LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies](https://mlsanity.com/paper/2606.15768/) (2026)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks](https://mlsanity.com/paper/2502.17157/) (2025)
- [τ0-WM: A Unified Video-Action World Model for Robotic Manipulation](https://mlsanity.com/paper/2606.01027/) (2026)
- [Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow](https://mlsanity.com/paper/2512.24766/) (2025)
- [FlowWAM: Optical Flow as a Unified Action Representation for World Action Models](https://mlsanity.com/paper/2607.13017/) (2026)
- [WAM4D: Fast 4D World Action Model via Spatial Register Tokens](https://mlsanity.com/paper/2606.14048/) (2026)
- [Video Generation Models are General-Purpose Vision Learners](https://mlsanity.com/paper/2607.09024/) (2026)
- [Action Images: End-to-End Policy Learning via Multiview Video Generation](https://mlsanity.com/paper/2604.06168/) (2026)
- [GeoSem-WAM: Geometry- and Semantic-Aware World Action Models](https://mlsanity.com/paper/2606.03188/) (2026)
- [DreamWAM: Beyond RGB Future Prediction for World Action Models](https://mlsanity.com/paper/2608.04996/) (2026)

## Abstract (arXiv)

World action models (WAMs) have advanced robot control by predicting how observations and actions evolve over time. Despite this progress, RGB and action based future prediction does not explicitly address the spatial understanding needed for robot manipulation. Existing efforts often add a limited set of spatial prediction tasks through specialized heads or branches, leaving both the range of spatial supervision and the model architecture fragmented. We introduce XGenAct, a world action model that represents RGB observations, robot actions, metric depth, surface normals, and functional role segmentation as RGB videos through deterministic codecs. By sampling perception and action tasks during training, XGenAct uses one video diffusion transformer and one objective to learn temporal prediction across these spaces without modality specific learned heads. On held out RLBench tasks, structured perception training improves average closed loop success over RGB only training, and XGenAct achieves 52% success in the five task external comparison, versus 26% for the strongest evaluated baselines. It also predicts future depth and segmentation more accurately than the evaluated pipelines that generate RGB first and then apply a frozen perception expert.