top of page

CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models

​

Author(s)

P Hosseini, O Bohdal, T Ceritli, I Castro, M Purver, M Ozay, U Michieli

Abstract

​

More info

TBA

​

  • Bluesky_Logo wt
  • LinkedIn
  • YouTube
  • mastodon icon white

Copyright © 2023 iGGi

​

Privacy Policy

​

The EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (iGGi) is a leading PhD research programme aimed at the Games and Creative Industries.

bottom of page