AI RESEARCH
Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes
arXiv CS.LG
•
ArXi:2603.23507v1 Announce Type: cross While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this paper, we propose Deletion-Insertion Diffusion language models (DID) that rigorously formulate token deletion and insertion as discrete diffusion processes, replacing the masking and unmasking processes in current MDLMs. DID improves.