Author

Chenkai Xu

h-index 2 View on Semantic Scholar

We have 1 of 7 papers

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.

Preprint Aug 2026

CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing

This work presents Consistency Forcing (CForce) for dLLMs, a distillation method to force the mask predictions of early stages to align with those of later stages, thereby improving training-inference alignment.

Yujie Ren, Chenkai Xu, Zhuocheng Gong et al. · 1 citation