TheMatrixMaster/edit-flows-demo
Educational Implementation of "Edit Flows: Flow Matching with Edit Operations" by Havasi et al.
This educational project explores how AI can generate new sequences based on existing ones, particularly focusing on sine waves. It takes different starting patterns (priors) and transforms them into desired target patterns, illustrating how an AI model learns these transformations. This is useful for researchers and students in machine learning interested in sequence generation and transformation techniques.
Use this if you are a machine learning researcher or student wanting to understand the 'Edit Flows' technique for sequence generation and transformation.
Not ideal if you need a production-ready tool for generating or manipulating real-world sequential data like audio, text, or time series.
Stars
38
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TheMatrixMaster/edit-flows-demo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
tokkiwa/FlashGMM
Official repository for the paper “FlashGMM: Fast Gaussian Mixture Entropy Model for Learned...
beneboeck/sparse-bayesian-gen-mod
Source code of the Paper "Sparse Bayesian Generative Modeling for Compressive Sensing" (NeurIPS 24)
iwa-shi/CRDR
Official implementation of "Controlling Rate, Distortion, and Realism: Towards a Single...