Advances in Language Model Training

Researchers propose Rubric-Conditioned Self-Distillation, a new method for post-training reasoning language models. This approach aims to improve the learning process by addressing limitations in traditional supervised distillation and reinforcement learning.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementJun 17, 2026, 05:54 PM 80%

   Researchers propose Rubric-Conditioned Self-Distillation for improved language model training

   Researchers propose Rubric-Conditioned Self-Distillation, a new method for post-training reasoning language models. This approach aims to improve the learning process by addressing limitations in traditional supervised distillation and reinforcement learning.

   Read the full story →