# TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos

arXiv: https://arxiv.org/abs/2511.21690 · HTML: https://mlsanity.com/paper/2511.21690/

## Key facts

- Cited by 15 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 61 of its 65 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## 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 61)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics](https://mlsanity.com/paper/2406.10721/) (2024)
- [One-Shot Visual Imitation Learning via Meta-Learning](https://mlsanity.com/paper/1709.04905/) (2017)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023)
- [RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation](https://mlsanity.com/paper/1811.02790/) (2018)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [Learning to Act from Actionless Videos through Dense Correspondences](https://mlsanity.com/paper/2310.08576/) (2023)
- [Magma: A Foundation Model for Multimodal AI Agents](https://mlsanity.com/paper/2502.13130/) (2025)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [Flow as the Cross-Domain Manipulation Interface](https://mlsanity.com/paper/2407.15208/) (2024)

## Built on by (most cited first, 15 of 15)

- [4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere](https://mlsanity.com/paper/2602.10094/) (2026)
- [EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data](https://mlsanity.com/paper/2607.08436/) (2026)
- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior](https://mlsanity.com/paper/2603.25399/) (2026)
- [GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization](https://mlsanity.com/paper/2605.12369/) (2026)
- [DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation](https://mlsanity.com/paper/2605.30350/) (2026)
- [Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies](https://mlsanity.com/paper/2608.03727/) (2026)
- [μ0: A Scalable 3D Interaction-Trace World Model](https://mlsanity.com/paper/2606.13769/) (2026)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [GeomVLA: Unifying Scene, Motion, and Action in 3D](https://mlsanity.com/paper/2609.13812/) (2026)
- [JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation](https://mlsanity.com/paper/2609.25322/) (2026)
- [World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories](https://mlsanity.com/paper/2610.01742/) (2026)
- [Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics](https://mlsanity.com/paper/2610.13522/) (2026)
- [Box-WAM: Box Trajectories as Compact State Representations for World Action Models](https://mlsanity.com/paper/2610.17526/) (2026)

## Abstract (arXiv)

Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robots - are abundant, differences in embodiment, camera, and environment hinder their direct use. We address the small-data problem by introducing a unifying, symbolic representation - a compact 3D "trace-space" of scene-level trajectories - that enables learning from cross-embodiment, cross-environment, and cross-task videos. We present TraceGen, a world model that predicts future motion in trace-space rather than pixel space, abstracting away appearance while retaining the geometric structure needed for manipulation. To train TraceGen at scale, we develop TraceForge, a data pipeline that transforms heterogeneous human and robot videos into consistent 3D traces, yielding a corpus of 123K videos and 1.8M observation-trace-language triplets. Pretraining on this corpus produces a transferable 3D motion prior that adapts efficiently: with just five target robot videos, TraceGen attains 80% success across four tasks while offering 50-600x faster inference than state-of-the-art video-based world models. In the more challenging case where only five uncalibrated human demonstration videos captured on a handheld phone are available, it still reaches 67.5% success on a real robot, highlighting TraceGen's ability to adapt across embodiments without relying on object detectors or heavy pixel-space generation.