mlsanityData to 14 Oct 2026

SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs

arXiv 2606.04964 ↗First posted 3 Jun 2026cs.CLcited by 0

On the map: Diffusion models → Discrete and text diffusion

Abstract (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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 11 of its 18 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

11 of 18 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026T^star: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning16 Jan
  2. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct

Other references · 9

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  5. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 654
  6. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  7. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  8. 2025AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Sizecited by 31
  9. 2026DSB: Dynamic Sliding Block Scheduling for Diffusion LLMscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models
  2. 2026Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models
  3. 2026When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models
  4. 2026Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models
  5. 2026Dynamic Chunking for Diffusion Language Models
  6. 2026HaloBlock: Faster and Better Decoding for Diffusion Large Language Models
  7. 2025WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
  8. 2026GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models