length-control

Tag

Cards List
#length-control

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

Hugging Face Daily Papers · 2026-09-17 Cached

When2Think is a post-training framework that dynamically allocates computation in large reasoning models based on problem difficulty, improving accuracy-efficiency trade-offs on mathematical benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback