Language Models Can Rewrite Their Own Weights
A 27B model rewrites its own weights without gradients, gaining 6.6 points more accuracy on 490 unseen problems.
Wednesday, November 18: 1 frontier paper out of 443 read.
Papers rated as moving the field
How we chooseA 27B model rewrites its own weights without gradients, gaining 6.6 points more accuracy on 490 unseen problems.
Nov 12–18: 272 cleared, 18 frontier
Papers this week that name the model
Papers this week with an author at the lab
63 papers, by field