Rethinking Video Generation Model for the Embodied World

• URL: http://arxiv.org/abs/2601.15282v1
• Date: Wed, 21 Jan 2026 18:59:18 GMT
• Title: Rethinking Video Generation Model for the Embodied World
• Authors: Yufan Deng, Zilin Pan, Hongyu Zhang, Xiaojie Li, Ruoqing Hu, Yufei Ding, Yiming Zou, Yan Zeng, Daquan Zhou,
• Abstract summary: RBench is designed to evaluate robot-oriented video generation across five task domains and four distinct embodiments.<n> evaluation of 25 representative models highlights significant deficiencies in generating physically realistic robot behaviors.<n>We introduce a refined four-stage data pipeline, resulting in RoVid-X, the largest open-source robotic dataset for video generation with 4 million annotated video clips.
• Score: 26.174517437895616
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing high-quality videos that accurately reflect real-world robotic interactions remains challenging, and the lack of a standardized benchmark limits fair comparisons and progress. To address this gap, we introduce a comprehensive robotics benchmark, RBench, designed to evaluate robot-oriented video generation across five task domains and four distinct embodiments. It assesses both task-level correctness and visual fidelity through reproducible sub-metrics, including structural consistency, physical plausibility, and action completeness. Evaluation of 25 representative models highlights significant deficiencies in generating physically realistic robot behaviors. Furthermore, the benchmark achieves a Spearman correlation coefficient of 0.96 with human evaluations, validating its effectiveness. While RBench provides the necessary lens to identify these deficiencies, achieving physical realism requires moving beyond evaluation to address the critical shortage of high-quality training data. Driven by these insights, we introduce a refined four-stage data pipeline, resulting in RoVid-X, the largest open-source robotic dataset for video generation with 4 million annotated video clips, covering thousands of tasks and enriched with comprehensive physical property annotations. Collectively, this synergistic ecosystem of evaluation and data establishes a robust foundation for rigorous assessment and scalable training of video models, accelerating the evolution of embodied AI toward general intelligence.

Related papers

• D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping [66.22412592525369]
  We introduce a real-to-sim-to-real engine that leverages the Gaussian Splat representations to build a differentiable engine.<n>We show that our engine achieves accurate and robust performance in mass identification across various object geometries and mass values.<n>Those optimized mass values facilitate force-aware policy learning, achieving superior and high performance in object grasping.
  arXiv  Detail & Related papers  (2026-03-01T15:32:04Z)
• RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation [37.52152452548065]
  RoboGene is an agentic framework designed to automate the generation of diverse, physically plausible manipulation tasks.<n>We conduct extensive quantitative analysis and large-scale real-world experiments, collecting datasets of 18k trajectories.<n>Results demonstrate that RoboGene significantly outperforms state-of-the-art foundation models.
  arXiv  Detail & Related papers  (2026-02-18T13:29:43Z)
• Mirage2Matter: A Physically Grounded Gaussian World Model from Video [87.9732484393686]
  We present Simulate Anything, a graphics-driven world modeling and simulation framework.<n>Our approach reconstructs real-world environments into a photorealistic scene representation using 3D Gaussian Splatting (3DGS)<n>We then leverage generative models to recover a physically realistic representation and integrate it into a simulation environment via a precision calibration target.
  arXiv  Detail & Related papers  (2026-01-24T07:43:57Z)
• AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis [33.90053396451562]
  We introduce AnchorDream, an embodiment-aware world model that repurposes pretrained video diffusion models for robot data synthesis.<n>Our method scales them into large, diverse, high-quality datasets without requiring explicit environment modeling.<n>Experiments show that the generated data leads to consistent improvements in downstream policy learning, with relative gains of 36.4% in simulator benchmarks and nearly double performance in real-world studies.
  arXiv  Detail & Related papers  (2025-12-12T18:59:45Z)
• Invariance Co-training for Robot Visual Generalization [72.88252238231269]
  Reasoning from diverse observations is a fundamental capability for generalist robot policies to operate in a wide range of environments.<n>We show that co-training on diverse data improves performance by 18 percent over existing generative augmentation methods.
  arXiv  Detail & Related papers  (2025-12-04T20:08:46Z)
• Synthetic Dataset Generation for Autonomous Mobile Robots Using 3D Gaussian Splatting for Vision Training [0.708987965338602]
  We propose a novel method for automatically generating annotated synthetic data in Unreal Engine.<n>We demonstrate that synthetic datasets can achieve performance comparable to that of real-world datasets.<n>This is the first application of synthetic data for training object detection algorithms in robot soccer.
  arXiv  Detail & Related papers  (2025-06-05T14:37:40Z)
• ORV: 4D Occupancy-centric Robot Video Generation [33.360345403049685]
  Acquiring real-world robotic simulation data through teleoperation is notoriously time-consuming and labor-intensive.<n>We propose ORV, an Occupancy-centric Robot Video generation framework, which utilizes 4D semantic occupancy sequences as a fine-grained representation.<n>By leveraging occupancy-based representations, ORV enables seamless translation of simulation data into photorealistic robot videos, while ensuring high temporal consistency and precise controllability.
  arXiv  Detail & Related papers  (2025-06-03T17:00:32Z)
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models [120.25799361925387]
  DreamGen is a pipeline for training robot policies that generalize across behaviors and environments through neural trajectories.<n>Our work establishes a promising new axis for scaling robot learning well beyond manual data collection.
  arXiv  Detail & Related papers  (2025-05-19T04:55:39Z)
• WorldSimBench: Towards Video Generation Models as World Simulators [79.69709361730865]
  We classify the functionalities of predictive models into a hierarchy and take the first step in evaluating World Simulators by proposing a dual evaluation framework called WorldSimBench. WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks. Our comprehensive evaluation offers key insights that can drive further innovation in video generation models, positioning World Simulators as a pivotal advancement toward embodied artificial intelligence.
  arXiv  Detail & Related papers  (2024-10-23T17:56:11Z)
• RT-1: Robotics Transformer for Real-World Control at Scale [98.09428483862165]
  We present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks.
  arXiv  Detail & Related papers  (2022-12-13T18:55:15Z)
• MetaGraspNet: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis [78.26022688167133]
  We present a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis. The proposed dataset contains 100,000 images and 25 different object types. We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance.
  arXiv  Detail & Related papers  (2021-12-29T17:23:24Z)
• Maintaining a Reliable World Model using Action-aware Perceptual Anchoring [4.971403153199917]
  There is a need for robots to maintain a model of its surroundings even when objects go out of view and are no longer visible. This requires anchoring perceptual information onto symbols that represent the objects in the environment. We present a model for action-aware perceptual anchoring that enables robots to track objects in a persistent manner.
  arXiv  Detail & Related papers  (2021-07-07T06:35:14Z)

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.