# Mitty: Diffusion-based Human-to-Robot Video Generation

arXiv: https://arxiv.org/abs/2512.17253 · HTML: https://mlsanity.com/paper/2512.17253/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 52 of its 60 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 52)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://mlsanity.com/paper/2311.16498/) (2023)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer](https://mlsanity.com/paper/2504.20690/) (2025)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval](https://mlsanity.com/paper/2506.03141/) (2025)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models](https://mlsanity.com/paper/2502.01061/) (2025)
- [Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2405.01527/) (2024)
- [EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer](https://mlsanity.com/paper/2503.07027/) (2025)
- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [Towards An End-to-End Framework for Flow-Guided Video Inpainting](https://mlsanity.com/paper/2204.02663/) (2022)
- [VideoDex: Learning Dexterity from Internet Videos](https://mlsanity.com/paper/2212.04498/) (2022)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [To Create What You Tell: Generating Videos from Captions](https://mlsanity.com/paper/1804.08264/) (2018)
- [Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning](https://mlsanity.com/paper/2506.05207/) (2025)
- [Humanoid Policy ~ Human Policy](https://mlsanity.com/paper/2503.13441/) (2025)
- [Phantom: Training Robots Without Robots Using Only Human Videos](https://mlsanity.com/paper/2503.00779/) (2025)
- [Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks](https://mlsanity.com/paper/2501.15891/) (2025)

## Built on by (most cited first, 14 of 14)

- [StreamingEffect: Real-Time Human-Centric Video Effect Generation](https://mlsanity.com/paper/2605.17019/) (2026)
- [PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion](https://mlsanity.com/paper/2606.01399/) (2026)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling](https://mlsanity.com/paper/2604.28185/) (2026)
- [Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration](https://mlsanity.com/paper/2605.17423/) (2026)
- [HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing](https://mlsanity.com/paper/2608.12122/) (2026)
- [OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation](https://mlsanity.com/paper/2605.12038/) (2026)
- [H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models](https://mlsanity.com/paper/2608.13049/) (2026)
- [RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation](https://mlsanity.com/paper/2607.06558/) (2026)
- [SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution](https://mlsanity.com/paper/2605.19319/) (2026)
- [Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos](https://mlsanity.com/paper/2606.24448/) (2026)
- [RGB-D Video Generation for Improving Human-to-Robot Object Handover Prediction](https://mlsanity.com/paper/2608.13028/) (2026)
- [PAI-Actor: Cinematic Multi-Character Replacement in Dynamic Scenes](https://mlsanity.com/paper/2609.05918/) (2026)
- [HuRo: Robotizing Human Videos for Scalable VLA Pretraining](https://mlsanity.com/paper/2609.10706/) (2026)

## Abstract (arXiv)

Learning directly from human demonstration videos is a key milestone toward scalable and generalizable robot learning. Yet existing methods rely on intermediate representations such as keypoints or trajectories, introducing information loss and cumulative errors that harm temporal and visual consistency. We present Mitty, a Diffusion Transformer that enables video In-Context Learning for end-to-end Human2Robot video generation. Built on a pretrained video diffusion model, Mitty leverages strong visual-temporal priors to translate human demonstrations into robot-execution videos without action labels or intermediate abstractions. Demonstration videos are compressed into condition tokens and fused with robot denoising tokens through bidirectional attention during diffusion. To mitigate paired-data scarcity, we also develop an automatic synthesis pipeline that produces high-quality human-robot pairs from large egocentric datasets. Experiments on Human2Robot and EPIC-Kitchens show that Mitty delivers state-of-the-art results, strong generalization to unseen environments, and new insights for scalable robot learning from human observations.