# AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size

arXiv: https://arxiv.org/abs/2509.26432 · HTML: https://mlsanity.com/paper/2509.26432/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion LLM and MoE inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 40 of its 45 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- Efficient LLM inference and serving / [Diffusion LLM and MoE inference](https://mlsanity.com/inference/diffusion-llm-and-moe-inference/)

## Builds on (most cited first, 30 of 40)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://mlsanity.com/paper/2505.19223/) (2025)
- [MMaDA: Multimodal Large Diffusion Language Models](https://mlsanity.com/paper/2505.15809/) (2025)
- [Remasking Discrete Diffusion Models with Inference-Time Scaling](https://mlsanity.com/paper/2503.00307/) (2025)
- [DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation](https://mlsanity.com/paper/2506.20639/) (2025)
- [Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://mlsanity.com/paper/2508.02193/) (2025)
- [dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching](https://mlsanity.com/paper/2506.06295/) (2025)
- [dKV-Cache: The Cache for Diffusion Language Models](https://mlsanity.com/paper/2505.15781/) (2025)
- [Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing](https://mlsanity.com/paper/2508.09192/) (2025)
- [Accelerating Diffusion LLMs via Adaptive Parallel Decoding](https://mlsanity.com/paper/2506.00413/) (2025)
- [Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding](https://mlsanity.com/paper/2505.16990/) (2025)
- [LaViDa: A Large Diffusion Language Model for Multimodal Understanding](https://mlsanity.com/paper/2505.16839/) (2025)

## Built on by (most cited first, 30 of 31)

- [Attention Is All You Need for KV Cache in Diffusion LLMs](https://mlsanity.com/paper/2510.14973/) (2025)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [Deferred Commitment Decoding for Diffusion Language Models](https://mlsanity.com/paper/2601.02076/) (2026)
- [Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration](https://mlsanity.com/paper/2512.07173/) (2025)
- [DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs](https://mlsanity.com/paper/2602.05992/) (2026)
- [When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models](https://mlsanity.com/paper/2604.23994/) (2026)
- [Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving](https://mlsanity.com/paper/2512.17077/) (2025)
- [Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs](https://mlsanity.com/paper/2602.00879/) (2026)
- [Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models](https://mlsanity.com/paper/2604.08964/) (2026)
- [Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models](https://mlsanity.com/paper/2602.04399/) (2026)
- [Multi-Block Diffusion Language Models](https://mlsanity.com/paper/2606.29215/) (2026)
- [Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models](https://mlsanity.com/paper/2606.29275/) (2026)
- [VDLM: Variable Diffusion LMs via Robust Latent-to-Text Rendering](https://mlsanity.com/paper/2602.15870/) (2026)
- [DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference](https://mlsanity.com/paper/2604.15750/) (2026)
- [Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning](https://mlsanity.com/paper/2605.02263/) (2026)
- [Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference](https://mlsanity.com/paper/2605.09820/) (2026)
- [Dynamic Chunking for Diffusion Language Models](https://mlsanity.com/paper/2605.15676/) (2026)
- [Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs](https://mlsanity.com/paper/2607.14107/) (2026)
- [STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models](https://mlsanity.com/paper/2601.04205/) (2025)
- [Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models](https://mlsanity.com/paper/2605.11726/) (2026)
- [When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models](https://mlsanity.com/paper/2605.28181/) (2026)
- [SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs](https://mlsanity.com/paper/2606.04964/) (2026)
- [AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding](https://mlsanity.com/paper/2606.08411/) (2026)
- [CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference](https://mlsanity.com/paper/2608.11235/) (2026)
- [Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs](https://mlsanity.com/paper/2608.22367/) (2026)
- [Affix Cache for Diffusion Large Language Models](https://mlsanity.com/paper/2608.26140/) (2026)
- [Information-Guided Frontier Decoding: Contextual Utility-Driven Commitment in dMLLMs](https://mlsanity.com/paper/2608.26641/) (2026)
- [Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling](https://mlsanity.com/paper/2609.16450/) (2026)
- [Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach](https://mlsanity.com/paper/2609.26052/) (2026)
- [Faster Block-Diffusion Serving with Distribution-Free Risk Guarantees](https://mlsanity.com/paper/2609.33887/) (2026)

## Abstract (arXiv)

Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, block-wise semi-autoregressive (semi-AR) approaches are widely adopted due to their support for KV caching and their favorable accuracy-speed trade-off. However, this paper identifies two fundamental limitations in the conventional semi-AR decoding approach that applies a fixed block size: i) late decoding overhead, where the unmasking of high-confidence tokens outside the current block is unnecessarily delayed, and ii) premature decoding error, where low-confidence tokens inside the current block are committed too early, leading to incorrect tokens. This paper presents the first systematic investigation challenging the fixed block size setting in semi-AR decoding. Through a statistical analysis of confidence dynamics during the denoising process, we identify a volatility band (VB) region during dLLM decoding, which encodes local semantic structure and can be used to guide adaptive block sizing. Leveraging these insights, we introduce AdaBlock-dLLM, a training-free, plug-and-play scheduler that adaptively aligns block boundaries with semantic steps by adjusting block size during runtime. Extensive experiments across diverse benchmarks show that AdaBlock-dLLM achieves up to 5.3% accuracy improvement under the same throughput budget. Beyond inference-time optimization, we hope our semantics-aware adaptive scheduling approach and confidence-based analysis will inspire future training strategies for dLLMs. Our code is available at https://github.com/lgxi24/AdaBlock-dLLM.