yulewang97/ERDiff

[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure in Latent Dynamics Alignment with Diffusion Models"

46
/ 100
Emerging

Uses diffusion models as a generative prior to align neural latent dynamics across sessions while preserving spatio-temporal structure. The approach combines diffusion-guided maximum likelihood alignment with linear probing layers initialized for stability, enabling recovery of consistent neural representations without requiring explicit correspondence. Targets neuroscience applications analyzing neural recordings across multiple recording sessions or experimental conditions.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

51

Forks

6

Language

Python

License

MIT

Last pushed

Feb 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yulewang97/ERDiff"

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