Author

Fengzhou Li

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Curriculum Learning for Countdown Reasoning in RL Fine-Tuning: Static Schedules Help, Adaptive Frontiers Forget

The novelty is twofold: tying curriculum design to the non-degeneracy of the RLOO advantage, and a zero-overhead adaptive sampler that discovers diﬃculty from reward rather than from a hand-set proxy.

Fengzhou Li · 0 citations