# CDVAE Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/cdvae
> Markdown URL: https://aitinkerers.org/technologies/cdvae.md
> Technology record last updated: 2026-05-26T00:00:39Z
> Generated: 2026-09-21T00:45:01Z

An SE(3)-invariant generative model that designs stable, periodic crystal structures by coupling variational autoencoders with diffusion processes.

Developed to bypass the limitations of traditional, grid-based material generation, the Crystal Diffusion Variational Autoencoder (CDVAE) targets the direct design of periodic material structures. The framework encodes a crystal's periodic lattice alongside its atomic coordinates and types into a continuous latent space. During decoding, a diffusion process iteratively updates atomic positions and species to satisfy physical bonding preferences, outputting stable structures while respecting translation, rotation, and permutation invariances. Tested on standard benchmarks like MP-20 and Carbon-24, CDVAE enables researchers to reconstruct structures, generate realistic materials, and optimize specific target properties via latent-space search.

- Official technology site: https://github.com/txie-93/cdvae
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Transformer-Diffusion model for molecular battery material generation](https://dubai.aitinkerers.org/talks/rsvp_SK0KgeEQ2Rc)

I built Simer Energy, an end-to-end generative AI pipeline that uses a hybrid Transformer-Diffusion architecture to autonomously design, physically relax and thermodynamically validate novel battery materials from scratch. For the demo, I will execute a terminal-based run of the by inputting strict material constraints (e.g., elemental bounds for a cobalt-free transition metal oxide, target stoichiometry, and symmetry parameters) into a fine-tuned model. I’ll show how the Transformer maps these constraints into a discretespace groups and passes it as a conditioning vector to a diffusion model. You will see the model denoise the 3D spatial atomic coordinates, followed by the critical "zero-strain" and then passing the raw generated structure directly into a Universal Machine Learning Force Field (CHGNet) to instantly relax the atomic coordinates, bypassing days of expensive DFT calculations and then run the relaxed structure through ALIGNN to validate its Energy Above Hull, resulting in a mathematically viable file generated in under three minutes.

- Event context: AI Tinkerers Dubai - May Demo Day — 2026-05-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_SK0KgeEQ2Rc

## Related Technologies

- [ALIGNN](https://aitinkerers.org/technologies/alignn) ([Markdown](https://aitinkerers.org/technologies/alignn.md)) — 1 public demo
- [Amazon SageMaker](https://aitinkerers.org/technologies/amazon-sagemaker) ([Markdown](https://aitinkerers.org/technologies/amazon-sagemaker.md)) — 2 public demos
- [AWS SageMaker](https://aitinkerers.org/technologies/aws-sagemaker) ([Markdown](https://aitinkerers.org/technologies/aws-sagemaker.md)) — 2 public demos
- [CHGNet](https://aitinkerers.org/technologies/chgnet) ([Markdown](https://aitinkerers.org/technologies/chgnet.md)) — 1 public demo
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [Llama 3](https://aitinkerers.org/technologies/llama-3) ([Markdown](https://aitinkerers.org/technologies/llama-3.md)) — 38 public demos
- [Meta Llama 3](https://aitinkerers.org/technologies/meta-llama-3) ([Markdown](https://aitinkerers.org/technologies/meta-llama-3.md)) — 1 public demo
- [NVIDIA A10G](https://aitinkerers.org/technologies/nvidia-a10g) ([Markdown](https://aitinkerers.org/technologies/nvidia-a10g.md)) — 1 public demo
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [unsloth](https://aitinkerers.org/technologies/unsloth) ([Markdown](https://aitinkerers.org/technologies/unsloth.md)) — 8 public demos