arxiv
PublishedMay 18, 2026 at 4:00 AM
—neutral
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
Publisher summary· verbatim
arXiv:2605.15609v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iterations still makes inference expensiv
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivMODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning5harxivPosition: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!5harxivGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions5harxivThe Impossibility of Eliciting Latent Knowledge5hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗