1
Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs
提出Predict-then-Diffuse框架，根据计算预算自适应调整响应长度，显著提升扩散LLM推理效率与吞吐量。
arXiv:2605.04215v2 Announce Type: replace-cross Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative …