Get Started
Home
Topics
Search
Library
Research questionHow can diffusion language models adapt infilling span lengths without sacrificing quality or inference speed?Infilling quality depends on the missing span's length, yet diffusion language models typically require that length before generation. Existing adaptive approaches can be sensitive to their starting length or add costly length changes and repeated searches.
AI
Code Generation & Program Synthesis
Diffusion Models
Inference Optimization
Natural Language Processing
Latest papersRecent research connected to this question, newest first.Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language ModelsApplies to diffusion language models performing text and code infilling. The reported evidence covers five models and eight benchmarks, using code pass rate, text BLEU-2, and inference-time comparisons; it does not establish performance beyond those settings.research paper · Sep 2, 2026
Related questions
How can continuous diffusion language models reduce denoising steps without sacrificing text-generation quality?How can autoregressive LLM decoding generate multiple tokens in parallel at large batch sizes without sacrificing quality?How can streaming video-language models cut frame-encoding latency while preserving question-relevant evidence?How can large language models cut training and inference costs without materially harming accuracy?