# 3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs

arXiv: https://arxiv.org/abs/2508.08821 · HTML: https://mlsanity.com/paper/2508.08821/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- 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, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers](https://mlsanity.com/paper/2311.15475/) (2023)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting](https://mlsanity.com/paper/2402.07207/) (2024)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [Pre-training without Natural Images](https://mlsanity.com/paper/2101.08515/) (2021)
- [GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs](https://mlsanity.com/paper/2312.00093/) (2023)
- [Learning to See by Looking at Noise](https://mlsanity.com/paper/2106.05963/) (2021)
- [LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models](https://mlsanity.com/paper/2411.09595/) (2024)
- [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023)
- [SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning](https://mlsanity.com/paper/2104.05832/) (2021)
- [StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts](https://mlsanity.com/paper/2204.08292/) (2022)

## Built on by (most cited first, 1 of 1)

- [Design-Specification Tiling for ICL-based CAD Code Generation](https://mlsanity.com/paper/2603.12712/) (2026)

## Abstract (arXiv)

Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a novel framework that enables the generation of 3D object prototypes directly from MLLMs, including geometry and part labels. Our pipeline is agentic, comprising a designer, coder, and visual inspector operating in a refinement loop. Notably, our approach requires no additional training data or detailed user instructions. Building on prior work in 2D generation, we demonstrate that rendered images produced by our framework can be effectively used for image classification pretraining tasks and outperforms previous methods by 15%. As a compelling real-world use case, we show that the generated prototypes can be leveraged to improve fine-grained vision-language models by using the rendered, part-labeled prototypes to fine-tune CLIP for part segmentation and achieving a 55% accuracy improvement without relying on any additional human-labeled data.