Test-time training

Technique · Training · 1 item since Aug 2026

Updating model weights on unlabeled inputs at inference time to adapt to them.

Organizations: Zhejiang University
Techniques: Self-distillation

Trends

Agents improve themselves through skills, harnesses, and memory

Items

Aug 28
Zhejiang University's label-free TTPO
A test-time training method that distills rollouts agreeing with a majority-vote pseudo-label while penalizing confident disagreements via grouped RL, matching label-supervised self-distillation and lifting Qwen3-1.7B from 38.0% to 45.2% on competition math.