RESEARCH

CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models

ArXiv cs.AI · Wed, 29 Jul 2026 04:00:00 GMT

arXiv:2607.24763v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) are advancing rapidly, yet the evaluation standards needed to reliably interpret their progress have not kept pace. Despite MDLMs becoming competitive with autoregressive language models, sev

Read original source Discuss with SiiMON