Researchers introduced a trajectory-level speculative decoding framework for diffusion-based language models (dLLMs) that reduces denoising iterations by 30-40% and increases tokens-per-step from 2.6 …
Researchers introduced ACache, an affix-oriented cache reuse mechanism for Diffusion Large Language Models (DLLMs) that selectively recomputes key-value states of critical Anchor Tokens to maintain ac…
Researchers found that safety alignment in Diffusion Large Language Models (DLLMs) is sparse and transferable, enabling attacks that increase attack success rates from 2.6% to 73.8% on LLaDA and from …
BlockServe, a continuous batching framework for diffusion large language models (dLLMs), achieves 1.9–10.6× throughput over Fast-dLLM across five benchmarks by integrating block-grained scheduling, mi…
Researchers have developed Fast-dLLM++, a training-free extension to diffusion large language models that accelerates inference by selecting parallel token commit sets based on the full sorted confide…