AIME26

Researchers compared six offline reinforcement-learning methods for distilling reasoning from large language models into smaller ones, finding that SFT, RFT, and RIFT produce nearly identical weight u…

Researchers developed VibeThinker-3B, a 3-billion-parameter language model that achieves reasoning performance matching or exceeding models orders of magnitude larger, scoring 94.3 on AIME26 and 80.2 …

Researchers have developed Self-Verified Distillation, a method allowing large language models to improve themselves using only unlabeled prompts without external feedback. The approach, tested on Qwe…