pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Learnability-Informed Fine-Tuning of Diffusion Language Models

cs.CL · 2026-05-21 · unverdicted · novelty 7.0

LIFT is a learnability-informed SFT algorithm for diffusion LMs that aligns token difficulty with diffusion time steps, yielding up to 3x gains on AIME'24 and AIME'25 over standard SFT baselines.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learnability-Informed Fine-Tuning of Diffusion Language Models cs.CL · 2026-05-21 · unverdicted · none · ref 20

    LIFT is a learnability-informed SFT algorithm for diffusion LMs that aligns token difficulty with diffusion time steps, yielding up to 3x gains on AIME'24 and AIME'25 over standard SFT baselines.