pith. sign in

Train long, think short: Curriculum learning for efficient reasoning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Training-Trajectory-Aware Token Selection

cs.CL · 2026-01-15 · unverdicted · novelty 6.0

Training-Trajectory-Aware Token Selection (T3S) reconstructs the token-level training objective to overcome a performance bottleneck in continual distillation of reasoning capabilities from large to small language models.

citing papers explorer

Showing 2 of 2 citing papers.