White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? (arxiv.org)

1 points by haltist 2y ago ↗ HN

0 comments

[ 2.9 ms ] story [ 8.0 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats