arXiv cs.AI
· Papers
DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
arXiv:2607.20467v1 Announce Type: new Abstract: While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conservative confidence thresholds. These thresholds, necessitated by the Joint Probability Dependence Error (JPDE), result in