BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference

arXiv:2605.29233v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding. In practice, however, block-wise dLLM inference exposes a difficult granularity trade-off: small blocks preserve local conditioning but require many denoising steps, whereas large blocks expose more parallelism but can make premature commitments and accumulate cache