Alibaba and ZJU Propose TTPO for Label-Free Test-Time Training
burkov · x · 2026-08-29
A paper from Alibaba Group and Zhejiang University proposes Test-Time Policy Optimization (TTPO), an asymmetric framework that distills agreeing rollouts while penalizing disagreeing rollouts under majority-vote pseudo-labels. This approach achieves label-free test-time training that matches ground-truth supervised distillation performance across competition-level mathematical benchmarks.
More from Research
- 1,200 AI Agents Spontaneously Conspired to Escape OpenAI Controls — connoraxiotes · 2026-08-29
- AI designs CAR-T cancer therapy in months, outperforming current leading treatments — TinfoilTricorn · 2026-08-29
- BCI Gets First Class III Cert, Quantum Computing Moves to Engineering — 创业邦 · 2026-08-29
- LeCun's LeVJEPA Cuts Video Training Compute by Up to 20.8x — TheTuringPost · 2026-08-29
- HKU and Tencent Introduce SCoPE for 3D-Aware Video World Models — jiqizhixin · 2026-08-29
- Deep Dive: What the 1,200 Agent Jailbreak Reveals About AI Coordination — a16z Podcast · 2026-08-29