# Learning Transferable World-Action Models from Task-Paired Human Videos

arXiv: https://arxiv.org/abs/2610.14351 · HTML: https://mlsanity.com/paper/2610.14351/

## 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 42 of its 46 references that are in the map.
- First posted on arXiv 9 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 42)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [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)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (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)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation](https://mlsanity.com/paper/2412.13877/) (2024)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [RoboVQA: Multimodal Long-Horizon Reasoning for Robotics](https://mlsanity.com/paper/2311.00899/) (2023)
- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025)
- [EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data](https://mlsanity.com/paper/2602.16710/) (2026)
- [In-Context Imitation Learning via Next-Token Prediction](https://mlsanity.com/paper/2408.15980/) (2024)
- [EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World](https://mlsanity.com/paper/2604.07607/) (2026)
- [Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers](https://mlsanity.com/paper/2403.12943/) (2024)
- [Learning Latent Action World Models In The Wild](https://mlsanity.com/paper/2601.05230/) (2026)
- [Emergence of Human to Robot Transfer in Vision-Language-Action Models](https://mlsanity.com/paper/2512.22414/) (2025)
- [Retrieval-Augmented Diffusion Models for Time Series Forecasting](https://mlsanity.com/paper/2410.18712/) (2024)
- [R+X: Retrieval and Execution from Everyday Human Videos](https://mlsanity.com/paper/2407.12957/) (2024)

## Abstract (arXiv)

World-action models inherit broad visual and physical priors from video pre-training. However, standard within-video next-frame prediction allows them to rely on appearance shared between the context and future, rather than learning interactions that transfer across scenes and embodiments. We introduce WATCH, a cross-video pre-training that learns from task-paired human demonstrations collected across diverse environments. Conditioned on the video and actions of one demonstration, the model jointly predicts another demonstration's actions and future frames from its current observation. Predicting one demonstration from another encourages the model to learn task-relevant interactions that transfer across scenes and demonstrators. Our pre-training shows that these capabilities can be learned from readily scalable human-human pairs alone, without requiring matched human-robot demonstrations. Analyses before robot post-training show improved motion alignment across embodiments and better action and video prediction on unseen robots, with representations closer to those learned from robot pairs. After robot post-training, WATCH improves MimicDroid in-context success from 40.9% to 68.3% with Cosmos Policy and from 59.8% to 77.7% with Cosmos3, with the largest gains on the unseen levels. Gains persist under context-free post-training across robot embodiments. WATCH outperforms within-video pre-training and co-training baselines, supporting cross-video prediction as a scalable approach to learning transferable world-action representations.