Author

Chia-Ming Lee

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.

#natural language process... Oct 2026

Where and When to Commit: Candidate-Aware Decoding for Diffusion Language Models

A training-free, candidate-aware early-exit framework that keeps the two axes separate and matches each decision to evidence of its own scope is introduced, referred to as LATCH ( Localized Acceleration with Tracked-Candidate Halting ).

Chia-Ming Lee, Ming-Ching Chang, Xin Li et al. · arXiv.org · 0 citations