1 year ago|discuss
user: mluo
51 karma | created 3 years ago
recent submissions
1 year ago|discuss
1 year ago|discuss
1 year ago|discuss
1 year ago|discuss
1 year ago|discuss
1 year ago|discuss
1 year ago|discuss
1 year ago|discuss
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL
(pretty-radio-b75.notion.site)
19 pts|1 year ago|discuss
2 years ago|discuss
3 years ago|discuss