mlsanityData to 14 Oct 2026

LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory

arXiv 2605.02288 ↗First posted 4 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the protocol grounding and layout-level safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are realistic and valid under modeled geometric, chemical-safety, and navigation constraints.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 4 May 2026.

Builds on

28 of 43 references.

References · 28

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  3. 2025Gemma 3 Technical Reportcited by 1,824
  4. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  5. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  6. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  7. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  8. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  9. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  10. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
  11. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  12. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
16 more
  1. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  2. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  3. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 193
  4. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 166
  5. 2020SceneFormer: Indoor Scene Generation with Transformerscited by 158
  6. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 125
  7. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 96
  8. 2023AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homescited by 82
  9. 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agentcited by 56
  10. 2025NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidancecited by 49
  11. 2023iPlanner: Imperative Path Planningcited by 37
  12. 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placementcited by 25
  13. 2024ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretrainingcited by 19
  14. 2023Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedbackcited by 17
  15. 2024AutoDSL: Automated domain-specific language design for structural representation of procedures with constraintscited by 6
  16. 2025ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Datacited by 3

Built on by

Not cited yet.