Update README.md

README.md

@@ -45,6 +45,10 @@ best.save("fig.tex")
 ```
 
 ## Changes from DeTi*k*Zify<sub>v1</sub>
+We document all changes between DeTikZify<sub>v1</sub> and
+DeTikZify<sub>v2</sub> in our paper, "[TikZero: Zero-Shot Text-Guided Graphics
+Program Synthesis](https://arxiv.org/abs/2503.11509)". For convenience, they
+are also listed below.
 
 ### Architecture
 Similar to DeTi*k*Zify<sub>v1</sub>, DeTi*k*Zify<sub>v2</sub> uses a SigLIP
@@ -59,8 +63,9 @@ frozen but fully fine-tuned with the rest of the model.
 For pretraining, we switch from MetaFig to the much larger
 [ArXivCap](https://huggingface.co/datasets/MMInstruction/ArxivCap) dataset and
 extract 1 million (figure, caption, OCR) tuples for pretraining the modality
-connector. For fine-tuning, we create a new DaTi*k*Z<sub>v3</sub> dataset (to
-be released soon) with over 450k Ti*k*Z drawings.
+connector. For fine-tuning, we create the new
+[DaTi*k*Z<sub>v3</sub>](https://huggingface.co/datasets/nllg/datikz-v3) dataset
+with over 450k Ti*k*Z drawings.
 
 We also train a new model called
 [UltraSketch](https://huggingface.co/nllg/ultrasketch) to generate synthetic