HackerTrans
TopNewTrendsCommentsPastAskShowJobs

at2005

no profile record

Submissions

Matrix Orthogonalization Improves Memory in Recurrent Models

ayushtambde.com
85 points·by at2005·14 วันที่ผ่านมา·32 comments

Tree Search Distillation for Language Models Using PPO

ayushtambde.com
87 points·by at2005·4 เดือนที่ผ่านมา·10 comments

comments

at2005
·4 เดือนที่ผ่านมา·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
·4 เดือนที่ผ่านมา·discuss
Ah, I meant that MCTS uses more inference-time compute (over GRPO) to produce a training sample