TwiScan 热门 社区 账号集合
登录 注册

注册并分享邀请链接，可获得视频播放与邀请奖励。

立即注册
Sriraam
@27upon2
post-training research @chakra_ai prev harvard
加入 July 2016
4.1K 正在关注    2.2K 粉丝
Sriraam@27upon2
2026.06.16 19:34
We’re going back to PPO everybody. Curious if there’s some research or experiments comparing the stability with GRPO style setups when you have compacted rollouts
0
6
247
9
转发到社区