Xiuyu Li(@sheriyuo):A nice theoretical revisit of OPD. With the same supervision budget, supervising only the first 30% of tokens nearly matches standard OPD, while supervising only the last 30% barely works. Framing OPD as a constrained optimization problem naturally leads to an importance-weighted objective, resulting in IW-OPD, which improves sample efficiency and performance with no extra inference cost. Paper: https://t.co/ABztcquS6a Blog:

Xiuyu Li

@sheriyuo

Researcher @StepFun_ai | Working on long-horizon tasks | Prev @RUC1937 | Opinions are my own

加入 February 2026

1.8K 正在关注 13.4K 粉丝

Xiuyu Li@sheriyuo

2026.06.27 14:04

A nice theoretical revisit of OPD. With the same supervision budget, supervising only the first 30% of tokens nearly matches standard OPD, while supervising only the last 30% barely works. Framing OPD as a constrained optimization problem naturally leads to an importance-weighted objective, resulting in IW-OPD, which improves sample efficiency and performance with no extra inference cost. Paper: Blog:

显示更多