Lune

ICML2026Top-tier venue

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

Jianbao Cao, zhangrui zhao, Bohan Feng, Zixuan Hu, Rui Li, Haiyuan Wan, Chenxi Li, jingyuan Li, Wenzhe Cai, LEI BAI, Wanli Ouyang, LINGYU DUAN

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Habitat 2.0: Training Home Assistants to Rearrange their Habitat cites Habitat: A Platform for Embodied AI Research
  • 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation cites Habitat: A Platform for Embodied AI Research
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on12

  1. Habitat: A Platform for Embodied AI ResearchManolis Savva, Jitendra Malik, Devi Parikh, Dhruv Batra et al.ICCV 2019 · 1,863 citations
  2. Habitat 2.0: Training Home Assistants to Rearrange their HabitatAndrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans et al.NeurIPS 2021 · 826 citations
  3. 🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural GenerationMatt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs et al.NeurIPS 2022 · 596 citations
  4. DreamFusion: Text-to-3D using 2D DiffusionBen Poole, Ajay Jain, Jonathan T. Barron, Ben MildenhallICLR 2023 · 463 citations
  5. LayoutGPT: Compositional Visual Planning and Generation with Large Language ModelsWeixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani et al.NeurIPS 2023 · 462 citations

Related papers

  1. WorldGen: From Text to Traversable and Interactive 3D WorldsDilin Wang, Hyunyoung Jung, Tom Monnier, Kihyuk Sohn et al.CVPR 2026 · 24 citations
  2. SceneLM: 3D-Aware Language Models for Editable 3D Scene SynthesisXingbo Yao, Xiaoyu Chen, Doudou Zhang, Mingzhi Sheng et al.ACL Findings 2026
  3. Scenethesis: A Language and Vision Agentic Framework for 3D Scene GenerationLu Ling, Chen-Hsuan Lin, Tsung-Yi Lin, Yifan Ding et al.ICLR 2026 · 74 citations
  4. Repurposing 3D Generative Model for Autoregressive Layout GenerationHaoran Feng, Yifan Niu, Zehuan Huang, Yangtian Sun et al.CVPR 2026 · 3 citations
  5. Holodeck: Language Guided Generation of 3D Embodied AI EnvironmentsYue Yang, Fan-Yun Sun, Luca Weihs, Eli VanderBilt et al.CVPR 2024 · 47 citations
Dusk over the sea between two cliffs drawn in fine vertical lines