paper-with-me

Papers

Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models

2026-02-04 · Yu Zhang, Xinchen Li, Jialei Zhou, Hongnan Ma, Zhongwei Wan, Yiwei Shi, Duoqian Miao, Qi Zhang, Longbing Cao arxiv

Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which inevitably fragments complete semantic or syntactic constituents, leading to suboptimal performance. Inspired by the entropy reduction hypothesis (ERH), we recognize that constituent boundaries offer greater opportunities for uncertainty reduction, which motivates us to employ entropy analysis for identifying constituent boundaries. Therefore, we propose Swordsman, an entropy-driven adaptive block-wise decoding framework for DLMs. Swordsman adaptively partitions blocks by identifying entropy shifts between adjacent tokens to better align with semantic or syntactic constituent boundaries. In addition, Swordsman dynamically adjusts unmasking thresholds conditioned on the real-time unmasking status within a block, further improving both efficiency and stability. As a training-free framework, supported by KV Cache, Swordsman demonstrates state-of-the-art performance across extensive evaluations.

📄 PDF Abstract BibTeX arXiv:2602.04399

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding

2023-04-05 · CVPR 2023 1 · Bowen Liu, Yu Chen, Rakesh Chowdary Machineni, Shiyu Liu 외

Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compre…

BenchmarkingMS-SSIMOptical Flow EstimationPrediction+3

Fuzzy clustering algorithms with distance metric learning and entropy regularization

2021-02-18 · Sara Ines Rizo Rodriguez, Francisco de Assis Tenorio de Carvalho

The clustering methods have been used in a variety of fields such as image processing, data mining, pattern recognition, and statistical analysis. Generally, the clustering algorithms consider all variables equally relev…

ClusteringMetric Learning

Summary Statistics for Partitionings and Feature Allocations

2013-10-01 · NeurIPS 2013 · Işık Barış Fidaner, Ali Taylan Cemgil

Infinite mixture models are commonly used for clustering. One can sample from the posterior of mixture assignments by Monte Carlo methods or find its maximum a posteriori solution by optimization. However, in some proble…

Clustering

Summary Statistics for Partitionings and Feature Allocations

2013-12-01 · NeurIPS 2013 12 · Isik B. Fidaner, Taylan Cemgil

Infinite mixture models are commonly used for clustering. One can sample from the posterior of mixture assignments by Monte Carlo methods or find its maximum a posteriori solution by optimization. However, in some proble…

Clustering

Partition Map-Based Fast Block Partitioning for VVC Inter Coding

2025-04-25 · Xinmin Feng, Zhuoyuan Li, Li Li, Dong Liu 외

Among the new techniques of Versatile Video Coding (VVC), the quadtree with nested multi-type tree (QT+MTT) block structure yields significant coding gains by providing more flexible block partitioning patterns. However,…

Quantization