註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Zhen Zhang
@zhenzhangzz
PhD @UCSB, BS @TsinghuaNLP. Post training, Efficiency. Prev intern @ByteDanceSeed_ RL scaling team
加入 June 2016
570 正在關注    594 粉絲
We think we’ve found a better path to continual post-training: merging models in input space. 🔹 A 256-token soft prompt (~0.01% of params) matches full-parameter RL 🔹 Plug-and-play composition: prompts trained separately just stack, with no joint training, and the combo beats the experts. No more MOPD! 🔹 Better OOD generalization, almost no forgetting 🔹 ~0 inference overhead, even with a different prompt per request. Built for personalization.
顯示更多
0
24
512
58
轉發到社區