Ismail Labiad
@is_labiad
๊ฐ์
June 2025
37 ํ๋ก์ ์ค 39 ํฌ
Repeated sampling is the default way to scale LLM reasoning at test time. But token level noise often produces many near duplicate attempts that follow the same high level idea.
๐งต How can we cover more of the solution space without sacrificing throughput?
๋ ๋ณด๊ธฐ
