You can deploy this model and start earning money today!

gregkseno/
csbm

Name: csbm
Availability: InStock

Views

No views yet

Categorical Schrödinger Bridge Matching (CSBM)

Grigoriy Ksenofontov, Alexander Korotin

This repository hosts the official checkpoints for the paper "Categorical Schrödinger Bridge Matching", accepted at ICML 2025.

📌 TL;DR

This paper extends the Schrödinger Bridge problem to work with discrete time and spaces.

💾 Checkpoints

CSBM

Dataset	Reference Process	α	N	Saved Iteration
Colored MNIST	gaussian	0.01	2, 4, 10, 25, 50, 100	3
Colored MNIST	uniform	0.01, 0.05	25	3
CelebA	uniform	0.01, 0.005	100	4
Amazon Review	uniform	0.01, 0.005	100	5

[!NOTE] Each experiment directory includes a config.yaml file with the full training configuration.

Additional Components

vqgan_celeba_f8_1024.ckpt — VQ-GAN pretrained on the CelebA dataset
tokenizer_amazon.json — Tokenizer trained on the Amazon Reviews dataset

🎓 Citation

bibtex

@inproceedings{
  ksenofontov2025categorical,
  title={Categorical {Schr\"odinger} Bridge Matching},
  author={Grigoriy Ksenofontov and Alexander Korotin},
  booktitle={Forty-second International Conference on Machine Learning},
  year={2025},
  url={https://openreview.net/forum?id=RBly0nOr2h}
}

🙏 Credits

Weights & Biases — experiment-tracking and visualization toolkit;
Hugging Face — Tokenizers and Accelerate libraries for tokenizer implementation, parallel training, and checkpoint hosting on the Hub;
D3PM — reference implementation of discrete-diffusion models;
Taming Transformers — original VQ-GAN codebase;
VQ-Diffusion — vector-quantized diffusion architecture;
MDLM — diffusion architecture for text-generation experiments;
ASBM — evaluation metrics and baseline models for CelebA face transfer;
Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising — processed Amazon Reviews dataset and sentiment-transfer baselines;
Inkscape — an excellent open-source editor for vector graphics.

gregkseno/csbm