Ground Truth.
AI, checked against the source.

← All topics

weak-to-strong

Everything on Ground Truth tagged “weak-to-strong” — 1 item.

A weaker model just taught a stronger one, by passing on the lesson instead of the answers News

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 improve a 7B student.