Update README.md

README.md

@@ -54,11 +54,16 @@ model-index:
 
 Independent reproduction of the paper [*"All-atom Diffusion Transformers: Unified generative modelling of molecules and materials"*](https://www.arxiv.org/abs/2503.03965), by [Chaitanya K. Joshi](https://www.chaitjo.com/), [Xiang Fu](https://xiangfu.co/), [Yi-Lun Liao](https://www.linkedin.com/in/yilunliao), [Vahe Gharakhanyan](https://gvahe.github.io/), [Benjamin Kurt Miller](https://www.mathben.com/), [Anuroop Sriram*](https://anuroopsriram.com/), and [Zachary W. Ulissi*](https://zulissi.github.io/) from FAIR Chemistry at Meta (* Joint last author).
 
-All-atom Diffusion Transformers (ADiTs) jointly generate both periodic materials and non-periodic molecular systems using a unified latent diffusion framework:
-- An autoencoder maps a unified, all-atom representations of molecules and materials to a shared latent embedding space; and
-- A diffusion model is trained to generate new latent embeddings that the autoencoder can decode to sample new molecules or materials.
+Note that these checkpoints are the result of an independent reproduction of this research by Chaitanya K. Joshi, and may not correspond to the exact models/performance metrics reported in the final manuscript.
+
+These checkpoints can be used to run inference as described in the [README on GitHub](https://github.com/facebookresearch/all-atom-diffusion-transformer/). Alternatively, here is a minimal script for loading an ADiT checkpoint:
+```python
+from src.models.ldm_module import LatentDiffusionLitModule
+ckpt_path = "path-to-ckpt-file"
+model = LatentDiffusionLitModule.load_from_checkpoint(ckpt_path)
+model.eval()  # for sampling and inference
+```
 
-![](https://github.com/facebookresearch/all-atom-diffusion-transformer/blob/fc4364c86531db395153e37707ec692dfd3408ec/ADiT.png)
 
 ## Citation