# GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

arXiv: https://arxiv.org/abs/2412.11198 · HTML: https://mlsanity.com/paper/2412.11198/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 72 of its 86 references that are in the map.
- First posted on arXiv 15 Dec 2024.

## 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 72)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)

## Built on by (most cited first, 30 of 78)

- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think](https://mlsanity.com/paper/2507.01467/) (2025)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [A Survey of World Models for Autonomous Driving](https://mlsanity.com/paper/2501.11260/) (2025)
- [A Survey: Learning Embodied Intelligence from Physical Simulators and World Models](https://mlsanity.com/paper/2507.00917/) (2025)
- [DriveLaW:Unifying Planning and Video Generation in a Latent Driving World](https://mlsanity.com/paper/2512.23421/) (2025)
- [Boosting Generative Image Modeling via Joint Image-Feature Synthesis](https://mlsanity.com/paper/2504.16064/) (2025)
- [Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance](https://mlsanity.com/paper/2512.08765/) (2025)
- [ReSim: Reliable World Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.09981/) (2025)
- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [Do World Action Models Generalize Better than VLAs? A Robustness Study](https://mlsanity.com/paper/2603.22078/) (2026)
- [VaViM and VaVAM: Autonomous Driving through Video Generative Modeling](https://mlsanity.com/paper/2502.15672/) (2025)
- [OmniNWM: Omniscient Driving Navigation World Models](https://mlsanity.com/paper/2510.18313/) (2025)
- [The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2502.10498/) (2025)
- [WorldMark: A Unified Benchmark Suite for Interactive Video World Models](https://mlsanity.com/paper/2604.21686/) (2026)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [The Reality Gap in Robotics: Challenges, Solutions, and Best Practices](https://mlsanity.com/paper/2510.20808/) (2025)
- [UniFuture: A 4D Driving World Model for Future Generation and Perception](https://mlsanity.com/paper/2503.13587/) (2025)
- [UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving](https://mlsanity.com/paper/2601.04453/) (2026)
- [StateSpaceDiffuser: Bringing Long Context to Diffusion World Models](https://mlsanity.com/paper/2505.22246/) (2025)
- [GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control](https://mlsanity.com/paper/2505.22421/) (2025)
- [MobileWorldBench: Towards Semantic World Modeling For Mobile Agents](https://mlsanity.com/paper/2512.14014/) (2025)
- [Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models](https://mlsanity.com/paper/2507.13162/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation](https://mlsanity.com/paper/2603.14948/) (2026)
- [Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis](https://mlsanity.com/paper/2603.13615/) (2026)

## Abstract (arXiv)

We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent motion and human poses. GEM generates paired RGB and depth outputs for richer spatial understanding. We introduce autoregressive noise schedules to enable stable long-horizon generations. Our dataset is comprised of 4000+ hours of multimodal data across domains like autonomous driving, egocentric human activities, and drone flights. Pseudo-labels are used to get depth maps, ego-trajectories, and human poses. We use a comprehensive evaluation framework, including a new Control of Object Manipulation (COM) metric, to assess controllability. Experiments show GEM excels at generating diverse, controllable scenarios and temporal consistency over long generations. Code, models, and datasets are fully open-sourced.