Breaking the Factorization Barrier in Diffusion Language Models

ArXi:2603.00045v2 Announce Type: replace-cross Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the "factorization barrier": the assumption that simultaneously predicted tokens are independent. This limitation forces a trade-off: models must either sacrifice speed by resolving dependencies sequentially or suffer from incoherence due to factorization.