Q*
HTML-код
- Опубликовано: 18 сен 2024
- Like 👍. Comment 💬. Subscribe 🟥.
🏘 Discord: / discord
github.com/hu-...
From r to Q∗: Your Language Model is Secretly a Q-Function
arxiv.org/pdf/...
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
arxiv.org/pdf/...