RobertCsordas/ndr

The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".

42
/ 100
Emerging

This project helps machine learning researchers explore and reproduce experiments from the paper "The Neural Data Router". You provide experiment configurations, and the system runs the neural network models, tracking their performance. The output includes experiment results and plots, enabling you to compare different model configurations and understand their generalization capabilities.

No commits in the last 6 months.

Use this if you are a machine learning researcher interested in understanding or reproducing experiments related to adaptive control flow in transformer models for systematic generalization.

Not ideal if you are looking for a pre-trained model or a library to directly apply a neural data router to a specific real-world task without research-focused experimentation.

deep-learning-research transformer-models neural-network-experimentation model-generalization ml-reproducibility
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

34

Forks

8

Language

Python

License

MIT

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/RobertCsordas/ndr"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.