𝙩𝙮≃𝙛{𝕩}^A𝕀²·ℙarad𝕚g𝕞
2周前
腾讯AI lab最近好像对in-context learning很关注 ICPO-In Context Steered Policy Optimization
𝙩𝙮≃𝙛{𝕩}^A𝕀²·ℙarad𝕚g𝕞
2周前
## MLPs can learn in-context (刚才看到一个帖子一个standford phd提到的,手一滑就不见了) One of the most under-rated empirical results of this year was the fact that MLPs can learn in-context [14]. This is surprising becaus
Silent Bird
3周前
奇怪了,那個時代法律程序還是要走的
马东锡 NLP
3个月前
旧时代你还在为 Agent 写prompt。 新时代的人们已经开始写Agentic prompt。