Cascade Reward Sampling for Efficient Decoding-Time Alignment (arxiv.org)

3 points by Garcia98 2y ago ↗ HN

0 comments

[ 8.7 ms ] story [ 35.4 ms ] thread

No comments yet.

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

Source · Live DB stats