# GaussianGPT: Autoregressive Transformer Generates Full 3D Scenes via Next-Token Prediction

_Research · published 2026-07-10_

Researchers from TU Munich have introduced GaussianGPT, an autoregressive transformer model that generates 3D Gaussian scenes through next-token prediction — offering an alternative to the diffusion and flow-matching approaches that dominate current 3D generative modeling. The pipeline first compresses Gaussian primitives into discrete tokens using a sparse 3D convolutional VQ-VAE, then models those token sequences with a causal transformer using 3D rotary positional embeddings.

Because scenes are built sequentially rather than refined holistically, GaussianGPT naturally supports scene completion, outpainting, temperature-controlled sampling, and flexible generation horizons. The work has been accepted to ECCV 2026, with training and inference code, pre-trained VQ-VAE, and GPT checkpoints now publicly available.

## Sources
- [github.com](https://github.com/nicolasvonluetzow/gaussiangpt)
---
Canonical: https://genbuzz.news/posts/gaussiangpt-autoregressive-transformer-generates-full-3d-scenes-via-next-token-prediction