Search: diffusion models

More than 1,000 papers match: here are the 1,000 most recent, ranked by relevance.

• SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields

  Baixin Li, Haiyun He · 11 September 2026 · Generative Adversarial Networks and Image Synthesis

  Watermarking diffusion language models (DLMs) requires mechanisms compatible with iterative parallel unmasking rather than autoregressive decoding. Existing sampling-based watermarking methods typically inject position-wise i.i.d. perturbations, which can be poorly aligned with DLM decoding dynamics…

• In-Place Instruction Following in Diffusion Language Models

  Zheng Nie, Zherui Li, Jiaming Zhang, Kun Wang, Zhenhong Zhou, Yufei Guo · 9 September 2026 · Large Language Models

  Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored at arbitrary output positions, a paradigm known as In-place Prompting (IPP). We formalize this as the In-place Instruction Following (IIF) task and co…

• Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One

  Fred Zhangzhi Peng, Kaiwen Zheng, Anru R. Zhang · 7 September 2026 · Model-Driven Software Engineering Techniques

  Language generation is almost universally treated as a sequential process: autoregressive models emit one token at a time, while diffusion language models replace token-level seriality with a long trajectory of iterative refinement. In this work, we introduce PlaidQ, a 0.7B continuous diffusion lang…

• Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges

  Chenqi Li, Minghui Min, Dusit Niyato, Wei Ni · 7 September 2026 · IoT and Edge/Fog Computing

  Diffusion language models (DLMs) offer a non-autoregressive alternative for mobile edge agentic artificial intelligence (AI) by refining tokens through iterative denoising rather than left-to-right decoding. Compared with autoregressive Transformer-based large language models (LLMs), DLMs can update…

• Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models

  Haobo Xu, Sirui Chen, Yuanchen Bei, Lingjie Chen, Yuchen Yan, Dongqi Fu, Jingrui He, Hanghang Tong · 3 September 2026 · Large Language Models

  Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive paradigm. With bidirectional attention and any-order generation, DLMs naturally fit infilling tasks, which require generating a middle span conditioned on both the prefix and the suffix. However, infillin…

• Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry

  Shengfang Zhai, Leo Marchyok, Yuling Shi, Huanran Chen, Yinpeng Dong, Jiaheng Zhang, Sanghyun Hong · 2 September 2026 · Cryptography and Data Security

  Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional context modeling. Despite growing interest in their generative capabilities, the privacy risks of DLMs remain underexplo…

• Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models

  Guoli Wang, Haonan Shi, Tu Ouyang, An Wang · 2 September 2026 · Large Language Models

  Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introduces two axes that can influence safety alignment: when tokens are generated during denoising and where they appear in the response. In this paper, we …

• Denoising Diffusion Generative Models Secretly Calculate Attentions

  Farzan Haddadi, Leila Monfared, Ebrahim Rezaii, Mohammadreza Malek-Mohammadi, Pejman Zakalvand, Narges Mokhtari · 2 September 2026 · Generative Adversarial Networks and Image Synthesis

  Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, we show that diffusion models also inherently use an attention mecha…

• Trajectory-Level Speculative Decoding for Diffusion Language Models

  Tianxiang Pan, Baitao Gong, Mo Guang, Hongwei Yong, Tianpeng Jiang, Yaqian Li, Zheng Cao, Kaiwen Long · 31 August 2026 · Power Systems and Technologies

  Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence, severely limiting throughput. Unlike autoregressive models where speculative decoding operates on token seq…

• Survival-Guided Length Control for Efficient Diffusion Language Models

  Ivan Kobyzev, Abbas Ghaddar, Yufei Cui · 28 August 2026 · Large Language Models

  Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the e…

• Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models

  Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar, Junpei Komiyama · 27 August 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain tasks. Unlike AR models, DLMs produce output through iterative denoising without a left-to-right order. To further improve the performance of DLMs, we i…

• Precipitation Downscaling Using Foundation Model-Conditioned Diffusion

  Victor Nascimento Ribeiro, Jorge Guevara, Jorge Sebastian Moraga, Chris Lucas, Natalie Lord, Andrew Taylor, Edward Lockhart, Will Trojak, Johannes Schmude, Anne Jones · 27 August 2026 · Climate variability and models

  High-resolution precipitation fields are essential for hydrological impact assessment, yet global climate model outputs are too coarse and biased for direct use. AI-based statistical downscaling with diffusion models offers a promising approach, but the mechanism by which large-scale atmospheric pre…

• Improved denoising diffusion probabilistic models with efficient non-diagonal covariance modeling

  Rui Xia, Ayan Das, Artem Artemev, Andi Zhang, Guillaume Hennequin, Alberto Bernacchia · 25 August 2026 · Image and Signal Denoising Methods

  The sampling process of Denoising Diffusion Probabilistic Models (DDPMs) can be accelerated by leveraging second-order information in the form of approximations to the denoising posterior covariance -- allowing samples of acceptable quality to be produced in fewer but larger sampling steps. Previous…

• Syntax-Guided Diffusion Language Models with User-Integrated Personalization

  Ruqian Zhang, Yijiao Zhang, Juan Shen, Zhongyi Zhu, Annie Qu · 25 August 2026 · Generative Adversarial Networks and Image Synthesis

  Large language models have made revolutionary progress in generating human-like text, yet their outputs often tend to be generic, exhibiting insufficient structural diversity, which limits personalized expression. Recent advances in diffusion models have opened new opportunities for improving langua…

• Accelerating Diffusion Language Models via Structured Suffix Modeling

  Zifeng Cheng, Keda Li, Zhiwei Jiang, Cong Wang, Fei Shen, Qing Gu · 25 August 2026 · Natural Language Processing Techniques

  Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple tokens in a single generation step. However, this parallelism comes with substantial computational overhead, as each step requires interactions with all suffix tokens. Existing methods typically redu…

• SelFusion: Self-distillation for Diffusion Language Models

  Hyeongsoo Lim, Jinyoung Kim, Eunseo Seo, Minho Jang, Jiwon Yoon · 25 August 2026 · Large Language Models

  Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) large language models (LLMs), but their degraded generation quality limits practical applicability. Although knowledge distillation (KD) can be a promising direction for improving performance, we empiri…

• CAI-DLLM: Convergence Aware Inference for Diffusion Language Models

  Farhana Amin, Sabiha Afroz, Dimitrios S. Nikolopoulos · 25 August 2026 · Large Language Models

  Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation costly, especially when the model continues to recompute tokens that are already stable. To address these limitations, we propose CAI-DLLM, a traini…

• Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models

  Yuanhao Ban, Jiaqi Feng, Hengguang Zhou, Xiaohuan Pei, Justin Cui, Cho-Jui Hsieh · 21 August 2026 · Generative Adversarial Networks and Image Synthesis

  Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Re…

• DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models

  Xin Zhang, Yili Wang, Yue Tan, Xin He, Yanyu Qian, Yixin Liu, Yi Chang, Shirui Pan, Xin Wang · 18 August 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation. However, similar to autoregressive LLMs, D-LLMs remain vulnerable to hallucinations, where fluent outputs may contain factually incorrect or unsupported content. Although existing hallucination detecti…

• Evaluating and Calibrating Diffusion Model-derived Uncertainty for Quantitative MRI Mapping

  Shishuai Wang, Stefan Klein, Juan A. Hernandez-Tamames, Dirk H. J. Poot · 13 August 2026 · Functional Brain Connectivity Studies

  Quantitative MRI (qMRI) provides standardised tissue parameter maps, but the reliability of deep learning-based qMRI mapping methods is often not explicitly characterised. In this work we systematically evaluate uncertainty maps for quantitative MRI derived from multiple inferences of a data-consist…

• CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

  Yifan Wu, Yufeng Zhang, Kenli Li · 13 August 2026 · Large Language Models

  Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon. Many predictions stabilize early, but blockwise decoding continues until all positions are resolved, causing repeated dense forward passes. Existing accelerators often rely on…

• DoseBridge: Denoising Diffusion Bridge Model for Dose Prediction in Lung Intensity-Modulated Proton Therapy

  Zerun Zhang, Xiaoda Cong, Xiangkun Xu, Peter Y. Chen, Xuanfeng Ding · 12 August 2026 · Advanced Radiotherapy Techniques

  Most radiotherapy dose-prediction models use only CT images and anatomical structures, although intensity-modulated proton therapy (IMPT) dose also depends strongly on beam geometry and available clinical datasets are often small. We present DoseBridge, a denoising diffusion bridge model that uses t…

• Physics-informed Diffusion Generative Model for Time-Series Data Synthesis in Dynamic Systems

  Haiteng Wang, Yunfei Zhu, Tao Wang, Yikang Li, Jiabao Dong, Xiaoge Zhang, Lei Ren · 12 August 2026 · Model Reduction and Neural Networks

  Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operational status of complex dynamical systems. However, collecting such data is often limited by harsh environments (e.g., high temperature and high pressur…

• Reducing Pretraining-Generation Mismatch in Diffusion Language Models

  Xiaocheng Lu, Huabin Liu, Song Guo, Jianguo Li · 11 August 2026 · Large Language Models

  Autoregressive language models align training and use: generation conditions on a clean prompt, and training predicts future tokens from clean left context. Diffusion language models offer parallel denoising, but native dLLM pretraining can randomly corrupt prompt and continuation tokens together, w…

• MRI super-resolution in ten sampling steps using a diffusion bridge model

  Mojtaba Safari, Hang Yu, Zach Eidex, Mingzhe Hu, Ryan J. Sanford, Alexandru Florea, Shansong Wang, Chih-Wei Chang, Erik H Middlebrooks, Aditya Juloori, Stanley L. Liauw, Ralph Weichselbaum, Xiaofeng Yang · 11 August 2026 · Advanced Neuroimaging Techniques and Applications

  Objective. MRI provides excellent soft-tissue contrast, but long acquisition times can cause patient discomfort and lead to motion artifacts, forcing a trade-off between spatial resolution and scan time. Diffusion-based super-resolution (SR) reconstructs high-resolution (HR) images from low-resoluti…