A
Jul 16, 2026A weaker model just taught a stronger one, by passing on the lesson instead of the answers
Researchers from Tsinghua and ByteDance show that a small model's reinforcement learning gains can be distilled into a larger, already-stronger model by transferring the change in the teacher's policy rather than its outputs, letting a 1.5B teacher i
Jul 16, 20264 min read0 reactions0 comments