Authors

Kecheng Chen

Publications 2

Preprint Open access

D-Loop: Looped Diffusion Drafting for Speculative Decoding

Kecheng Chen, Yuyang He, Cheng Gong et al. · 2026

Block diffusion accelerates speculative decoding by drafting multiple tokens in one forward pass. However, each position predicts a marginal distribution without observing earlier proposed tokens, limiting draft quality and acceptance length. We identify a concrete failure, the \emph{repetition trap}, in which neighbor …

Preprint Open access

How Should Diffusion Language Models Edit Code?

Xijia Tao, Ziru Liu, Shansan Gong et al. · 2026

Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked diffusion language models divide these responsibilities across four editing interfaces: whole-file rewriting, search-and-replace, locate-then-infill, and token-level editing. Experi …

Co-authors