# URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

arXiv: https://arxiv.org/abs/2511.00940 · HTML: https://mlsanity.com/paper/2511.00940/

## Key facts

- Cited by 21 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 21 of its 31 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects](https://mlsanity.com/paper/2308.07391/) (2023)
- [Grounded 3D-LLM with Referent Tokens](https://mlsanity.com/paper/2405.10370/) (2024)
- [URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images](https://mlsanity.com/paper/2405.11656/) (2024)
- [Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model](https://mlsanity.com/paper/2410.13882/) (2024)
- [LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding](https://mlsanity.com/paper/2312.14074/) (2023)
- [GPT4Point: A Unified Framework for Point-Language Understanding and Generation](https://mlsanity.com/paper/2312.02980/) (2023)
- [3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer](https://mlsanity.com/paper/2501.01163/) (2025)
- [CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects](https://mlsanity.com/paper/2303.15782/) (2023)
- [Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2311.15383/) (2023)
- [REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints](https://mlsanity.com/paper/2503.06677/) (2025)
- [Can 3D Vision-Language Models Truly Understand Natural Language?](https://mlsanity.com/paper/2403.14760/) (2024)
- [A New Era of Mobility: Exploring Digital Twin Applications in Autonomous Vehicular Systems](https://mlsanity.com/paper/2305.16158/) (2023)

## Built on by (most cited first, 21 of 21)

- [PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image](https://mlsanity.com/paper/2511.13648/) (2025)
- [Articraft: An Agentic System for Scalable Articulated 3D Asset Generation](https://mlsanity.com/paper/2605.15187/) (2026)
- [PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects](https://mlsanity.com/paper/2605.21572/) (2026)
- [ArtLLM: Generating Articulated Assets via 3D LLM](https://mlsanity.com/paper/2603.01142/) (2026)
- [SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge](https://mlsanity.com/paper/2512.01629/) (2025)
- [SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM](https://mlsanity.com/paper/2603.23386/) (2026)
- [Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control](https://mlsanity.com/paper/2606.14699/) (2026)
- [ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes](https://mlsanity.com/paper/2511.12977/) (2025)
- [MotionAnymesh: Physics-Grounded Articulation for Simulation-Ready Digital Twins](https://mlsanity.com/paper/2603.12936/) (2026)
- [3D Generation for Embodied AI and Robotic Simulation: A Survey](https://mlsanity.com/paper/2604.26509/) (2026)
- [ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics](https://mlsanity.com/paper/2605.16582/) (2026)
- [GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors](https://mlsanity.com/paper/2606.08440/) (2026)
- [PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets](https://mlsanity.com/paper/2608.08053/) (2026)
- [NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation](https://mlsanity.com/paper/2608.24212/) (2026)
- [DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation](https://mlsanity.com/paper/2609.23103/) (2026)
- [AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos](https://mlsanity.com/paper/2609.24487/) (2026)
- [ArtLang: Structured Language-to-Kinematics Grounding for Articulated 3D Actuation](https://mlsanity.com/paper/2608.15419/) (2026)
- [FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations](https://mlsanity.com/paper/2609.20817/) (2026)
- [Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoning](https://mlsanity.com/paper/2609.25741/) (2026)
- [FACT: Fidelity-Aware Construction of Articulated Twins](https://mlsanity.com/paper/2609.37067/) (2026)
- [ViewStruct: View-Grounded Articulation and Connectivity Inference](https://mlsanity.com/paper/2610.16793/) (2026)

## Abstract (arXiv)

Constructing accurate digital twins of articulated objects is essential for robotic simulation training and embodied AI world model building, yet historically requires painstaking manual modeling or multi-stage pipelines. In this work, we propose URDF-Anything, an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM). URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction. It implements a specialized [SEG] token mechanism that interacts directly with point cloud features, enabling fine-grained part-level segmentation while maintaining consistency with the kinematic parameter predictions. Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches regarding geometric segmentation (mIoU 17% improvement), kinematic parameter prediction (average error reduction of 29%), and physical executability (surpassing baselines by 50%). Notably, our method exhibits excellent generalization ability, performing well even on objects outside the training set. This work provides an efficient solution for constructing digital twins for robotic simulation, significantly enhancing the sim-to-real transfer capability.