Topics can overlap: a paper counts once in each of its topics, but only once in the total. A topic assignment does not prove quality or reproducibility.
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 error. Existing acceleration methods typically choose a single block size per request, leaving the complementarity among block sizes unused. We show t
Useful for: Not assessed · Limitation: Not assessed
2026-05-20T07:06:54Z · Inference acceleration, Long context · Source
Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without KV cache. Recent sparse attention methods for dLLMs mitigate this cost via block-sparse computation, which is applied only in later iterations when model performance is less sensitive to coarse-grained sparse approximation, but yields limited improvements in computational efficiency and acceleration. This motivates a finer-grained sparsification strategy that can be applied from earlier iterations and leverages reusa
Useful for: Not assessed · Limitation: Not assessed
Public snapshot dates
Collection recorded in this snapshot
Newest publication recorded in this snapshot
Snapshot generated
These are saved observations, not the last collector attempt or a guarantee of corpus completeness.