Home Knowledge Base DyLLM

DyLLM

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention

arXiv:2603.08026v2 Announce Type: replace Abstract: Masked diffusion language models enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation. However, their iterative denoising process remains computationally expensive because it repeatedly processes the entire sequence at every step. We observe that across these diffusion steps, most token representations remain stable; only a small subset, which we term salient tokens,...

arXiv CS 8d ago