Researchers have developed a new algorithm for constrained decoding in diffusion language models, enabling efficient sampling under constraints defined by finite automata. Tests on models like Dream-7…
Researchers introduced llada.cpp, the first NPU-aware inference framework for accelerating diffusion large language models on smartphones, achieving 17x-42x latency reduction over CPU baselines while …
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…
Researchers at arXiv have introduced "infilling extraction," a new method for extracting training data from diffusion language models (DLMs) that uses arbitrary binary masks instead of relying solely …