paper-with-me

Papers

SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs

2026-06-03 · Xinrui Song, Zhuoran Wang, Mingju Gao, Hao Tang arxiv

Diffusion language models (DLMs) generate text through iterative denoising, and blockwise decoding improves their practicality by committing tokens in local blocks. However, existing blockwise methods typically rely on fixed block sizes or delimiter-based runtime signals, which do not necessarily align with semantic boundaries. In this paper, we propose SemBlock, a semantic-boundary-driven dynamic block decoding framework for diffusion LLMs. SemBlock formulates dynamic block construction as semantic boundary prediction and trains lightweight predictors on frozen LLaDA hidden states. To provide supervision, we construct SemBound, a semantic-boundary dataset that derives boundary labels from discourse units, reasoning steps, and implementation spans across natural language, math, and code tasks. During inference, SemBlock uses predicted boundary probabilities to select the ending position of each dynamic block. Experiments on GSM8K, IFEval, MATH, and HumanEval show that SemBlock consistently improves over fixed-block decoding and AdaBlock. Our code is publicly available: https://github.com/TH-AI-Lab-PKU/SemBlock.

📄 PDF Abstract BibTeX arXiv:2606.04964

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers

2026-05-31 · Yiming Zhao arxiv

We present a post-training quantization (PTQ) approach for Wan2.1-T2V-14B, a 14-billion-parameter text-to-video diffusion transformer, targeting the W8A8 HiFloat8 (HiF8) format on Ascend 910B NPUs. A central challenge in…

Rare Text Semantics Were Always There in Your Diffusion Transformer

2025-10-04 · Seil Kang, Woojung Han, Dayun Ju, Seong Jae Hwang arxiv

Starting from flow- and diffusion-based transformers, Multi-modal Diffusion Transformers (MM-DiTs) have reshaped text-to-vision generation, gaining acclaim for exceptional visual fidelity. As these models advance, users …

Image Editing

Dynamic Chunking for Diffusion Language Models

2026-05-15 · Yichen Zhu, Xiaoming Shi, Peng Zhao, Weiyu Chen 외 arxiv

Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block conditioning. We argue that this rigid partit…

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models

2026-06-29 · Xingyu Mou, Zijin Huang, Tianze Zhang, Yuxin Ma 외 arxiv

Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping quadratic attention costs tractable. Yet blockwise generation…

Semantic Diffusion Network for Semantic Segmentation

2023-02-04 · NeurIPS 2022 9 · Haoru Tan, Sitong Wu, Jimin Pi

Precise and accurate predictions over boundary areas are essential for semantic segmentation. However, the commonly-used convolutional operators tend to smooth and blur local detail cues, making it difficult for deep mod…

DecoderSegmentationSemantic Segmentation