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

Source: [3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs](<https://www.sota2.com/research/paper/68fa7a971e209131cea84167>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:23:58.707Z

Authors: Noor Ahmed, Cameron Braunstein, Steffen Eger, Eddy Ilg

Published: 2025-08-12T10:21:59.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.08821>)

[PDF](<https://arxiv.org/pdf/2508.08821.pdf>)
