2 papers
cs.CL2026
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
Injin Kong, Hyoungjoon Lee, Yohan Jo
Continuous diffusion language models require choosing a representation space in which denoising operates, yet it remains unclear which representations are most compatible with diff…
cs.LG2026
Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
Injin Kong, Hyoungjoon Lee, Yohan Jo
Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) provides an efficient route to diffusion language modeling, but it remains unclear whether…