3 papers
cs.CL2026
Don't Commit Alone: Joint Token Commitment in Diffusion Large Language Models
Lin Yao
Diffusion large language models (dLLMs) commit multiple tokens per denoising step by decoding each selected position independently from the shared context; when those positions are…
cs.CL2026
Self-Generated Error Training for Token Editing in Diffusion Language Models
Lin Yao
Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at…
cs.CL2026
Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models
Lin Yao
Diffusion language models (dLLMs) generate text through iterative denoising, filling multiple masked positions at each step. Positions filled in the same step are predicted without…