Dispersion loss counteracts embedding condensation in small language models

chenliu-1996.github.io

Dispersion loss counteracts embedding condensation in small language models

chenliu-1996.github.io

RSS BotMB to Hacker NewsEnglish · 2 months ago

Dispersion loss (LM-Dispersion)

chenliu-1996.github.io

Dispersion loss counteracts embedding condensation and improves generalization in small language models (ICML 2026).

Comments

You must log in or # to comment.

Chat

Hacker News

hackernews

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se

Community locked: only moderators can create posts. You can still comment on posts.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Source of the RSS Bot

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
289 users / week
3.44K users / month
9.43K users / 6 months
2 local subscribers
5.39K subscribers
60.5K Posts
32.5K Comments
Modlog

mods:
patrick
cake
RSS Bot