Diffusion Language Models Are Natively Length-Aware
arXiv:2603.06123v1 Announce Type: new Abstract: Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over …
Vittorio Rossi, Giacomo Cir\`o, Davide Beltrame, Luca Gandolfi, Paul R\"ottger, Dirk Hovy
10 views