$μ_0$: A Scalable 3D Interaction-Trace World Model

• URL: http://arxiv.org/abs/2606.13769v2
• Date: Mon, 15 Jun 2026 06:13:42 GMT
• Title: $μ_0$: A Scalable 3D Interaction-Trace World Model
• Abstract summary: We present a scalable world model based on 3D traces.<n>Our TraceExtract system automatically extracts 3D supervision.<n>These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.
• Score: 54.38434730157622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels. Pixel-space video models provide broad visual priors but expend model capacity on dense appearance reconstruction, while direct action models require embodiment-specific labels that hinder scalability. We present $μ_0$, a scalable world model based on 3D traces. Rather than predicting dense pixels or directly modeling actions, $μ_0$ forecasts smooth 3D trajectories for salient interaction points such as objects, tools, hands, and contact regions, yielding a compact, embodiment-agnostic motion interface. To enable training from diverse video sources, our TraceExtract system automatically extracts 3D supervision by selecting keypoints, constructing globally aligned traces, and associating motion segments with hierarchical language captions. This TraceExtract supervision pretrains $μ_0$ by combining a pretrained vision-language backbone with a modular trace expert, which represents each query via B-spline control points and predicts future traces. Experiments show that $μ_0$ outperforms baselines in both 2D and 3D trace prediction, including trace prediction models and tokenized VLM methods. Because $μ_0$ is frozen and reusable, it can be paired with action experts for downstream robot embodiments. Despite action-free pretraining, the resulting trace-conditioned policies achieve performance competitive with VLA models pretrained with action supervision, such as $π_0$. These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.

Related papers

• KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding [58.541098216700796]
  evaluating the physical consistency of embodied world models is a critical open challenge.<n>Existing frameworks almost exclusively rely on Inverse Dynamics Models(IDMs) for action extraction.<n>We present KineBench, an IDM-free closed-loop benchmark for EWMs.
  arXiv  Detail & Related papers  (2026-07-22T08:04:17Z)
• Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control [86.64250947574749]
  Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations.<n>Recent neural networks can estimate the articulated structure of 3D objects, but their generalization remains limited by the scarcity of annotated data.<n>We introduce Instruct-Particulate, a model that takes a 3D mesh together with a target kinematic specification.
  arXiv  Detail & Related papers  (2026-06-12T17:59:36Z)
• AFUN: Towards an Affordance Foundation Model for Functionality Understanding [12.890216832485647]
  We present ourmodel, a step towards an affordance foundation model for functionality understanding.<n>We build a large-scale standardized data pipeline that converts heterogeneous robot, human, simulation, and real-world scan data into a shared affordance schema.<n>Ourmodel outperforms all baselines by a large margin across 8 test sets from 4 benchmarks.
  arXiv  Detail & Related papers  (2026-06-01T17:50:16Z)
• From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [71.22409934108924]
  Human videos are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation.<n>This survey provides a unified view of how human videos are transformed into effective knowledge for Vision-Language-Action (VLA) models.<n>We highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency.
  arXiv  Detail & Related papers  (2026-05-18T06:19:16Z)
• ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes [55.32681167870698]
  Video-informed Pose Spaces (ViPS) is a feed-forward framework that discovers the latent distribution of valid articulations for auto-rigged meshes.<n>ViPS transfers generative video priors into a universal distribution over a given rig parameterization.<n>Our evaluations show that ViPS matches the performance of state-of-the-art methods trained on synthetic artist-created 4D data in both plausibility and diversity.
  arXiv  Detail & Related papers  (2026-04-19T21:21:11Z)
• Which Reconstruction Model Should a Robot Use? Routing Image-to-3D Models for Cost-Aware Robotic Manipulation [14.047294299357352]
  Multiple reconstruction methods offer different cost-quality tradeoffs.<n>We propose SCOUT, a novel routing framework that decouples reconstruction scores into two components.<n>SCOUT supports arbitrary cost constraints at inference time, accommodating the multi-dimensional cost constraints common in robotics.
  arXiv  Detail & Related papers  (2026-03-29T18:23:28Z)
• CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning [43.7594705101778]
  We propose a joint unsupervised differentiable-rendering-based pre-training method for images and point clouds, termed CLAP.<n>Our method overcomes the computational hurdle by Curvature Sampling to select the more informative points/pixels for pre-training.<n>Experiments show that CLAP achieves up to 100% more performance gain as compared to previous SOTA pre-training methods.
  arXiv  Detail & Related papers  (2024-12-04T06:26:12Z)
• Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
  A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
  arXiv  Detail & Related papers  (2021-03-12T15:30:02Z)
• Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping [23.456046776979903]
  We propose to leverage multiview data of textitstatic points in arbitrary scenes (static or dynamic) to learn a neural 3D mapping module. The neural 3D mapper consumes RGB-D data as input, and produces a 3D voxel grid of deep features as output. We show that our unsupervised 3D object trackers outperform prior unsupervised 2D and 2.5D trackers, and approach the accuracy of supervised trackers.
  arXiv  Detail & Related papers  (2020-08-04T02:59:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.