HackerTrans
TopNewTrendsCommentsPastAskShowJobs

at2005

no profile record

Submissions

Matrix Orthogonalization Improves Memory in Recurrent Models

ayushtambde.com
85 points·by at2005·vor 13 Tagen·32 comments

Tree Search Distillation for Language Models Using PPO

ayushtambde.com
87 points·by at2005·vor 4 Monaten·10 comments

comments

at2005
·vor 4 Monaten·discuss
I didn't compare with the harness (focused on distillation) but the original ToT paper has a section on it: https://arxiv.org/abs/2305.10601
at2005
·vor 4 Monaten·discuss
Ah, I meant that MCTS uses more inference-time compute (over GRPO) to produce a training sample