Appears on
Articles3
Edsger W. Dijkstra Archive: Legacy of a Computing Science Pioneer
Insight
0
cs.utexas.edu8mo agoFast-dLLM: Training-Free Acceleration Method for Diffusion Language Models Using KV Cache and Parallel Decoding
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind autoregressive mo
Insight
0
arxiv.org8mo ago
Exploring the Connection Between Text Diffusion Models and BERT's Masked Language Modeling
Insight
0
nathan.rs8mo ago