AI RESEARCH
TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
arXiv CS.CL
•
ArXi:2604.00666v1 Announce Type: new Diffusion language models (DLMs) offer a promising path toward low-latency generation through parallel decoding, but their practical efficiency depends heavily on the decoding trajectory. In practice, this advantage often fails to fully materialize because standard