Search: diffusion models

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

• DiLaServe: High SLO Attainment Serving for Diffusion Language Models

  Tzu-Tao Chang, Benjamin Yuanyang Hong, Kiet Pham, Shivaram Venkataraman · 30 June 2026 · Parallel Computing and Optimization Techniques

  Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during each denoising step, they offer higher inference throughput while maintaining competitive quality. However, realizing the…

• Diffusion Model-Based Data Assimilation for Real-World Energy Consumption Forecasting

  Ruoyu Hu, Dahai Yu, Feng Bao, Guang Wang, Guannan Zhang · 29 June 2026 · Energy Load and Power Forecasting

  Accurate estimation and forecasting of energy consumption are important for power-system operation, planning, and demand-side management. In practice, however, complete and timely measurements may not always be available, and the observed data can be partial, noisy, or delayed. This motivates the us…

• Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation

  Yuhang Chen, Xianfeng Wu, Jinhao Duan, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Parish Aggarwal, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Tianlong Chen · 29 June 2026 · Large Language Models

  Discrete diffusion language models (dLLMs) recover masked tokens in parallel, offering significant speedups over autoregressive (AR) generation. However, such promising frameworks face a fundamental architectural design dilemma: \ding{182} Adopting bidirectional attention achieves strong generation …

• Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context

  Fitsum Reda, John Kamalu, Roger Waleffe, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro · 26 June 2026 · Large Language Models

  Diffusion language models offer a promising alternative to autoregressive models due to their potential for parallel and iterative generation. However, existing approaches use a single network for both context representation and iterative denoising, forcing one model to serve both roles and limiting…

• High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology

  Johannes Boehm, Bappaditya Dey · 24 June 2026 · Advanced Electron Microscopy Techniques and Applications

  Advanced semiconductor nodes drastically increased demand for Transmission Electron Microscopy (TEM), yet destructive sample preparation, slow imaging and high costs severely limit the availability of diverse datasets needed for downstream machine learning (ML). Synthetic data generation is becoming…

• When to Plan, When to Polish: Noise Level as a Granularity Axis for Diffusion Language Models

  Peihong Li, Yuanjie Shi, Yan Yan · 23 June 2026 · Language Development and Disorders

  Standard tokenwise diffusion LMs keep training corruption and inference commitment at token granularity throughout denoising. At high noise, this leaves scattered local fragments rather than coherent evidence, making it hard to form early coarse structure, exactly what planning-sensitive generation …

• Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models

  Jiawei Xu, Minghui Liu, Aakriti Agrawal, Yifan Chen, Furong Huang · 23 June 2026 · Large Language Models

  Masked diffusion language models decode by iteratively unmasking tokens, where the unmasking order defines an "order of thought" that strongly influences generation quality yet is typically chosen heuristically. We derive a tractable upper bound on the sequential decoding mismatch, measured by the K…

• PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

  Yueyi Sun, Yuhao Wang, Jason Li, Ye Tian, Tao Zhang, Jacky Mai, Yihan Wang, Haochen Wang, Jinbin Bai, Ling Yang, Yunhai Tong · 19 June 2026 · Multimodal Machine Learning Applications

  Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDL…

• Diffusion Language Models: An Experimental Analysis

  Thomas Bertolani, Davide Bucciarelli, Leonardo Zini, Marcella Cornia, Lorenzo Baraldi · 19 June 2026 · Large Language Models

  Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks. Recently, Diffusion Language Models (DLMs) have emerged as an alternative paradigm that generates text through iterative denoising rather th…

• DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models

  Zirui Wu, Lin Zheng, Jiacheng Ye, Shansan Gong, Xueliang Zhao, Yansong Feng, Wei Bi, Lingpeng Kong · 18 June 2026 · Generative Adversarial Networks and Image Synthesis

  Block diffusion language models accelerate decoding through parallel block-wise denoising, yet whether they can be reliably scaled for long chain-of-thought (CoT) reasoning remains unresolved. To this end, we develop DreamReasoner-8B, an open-source block diffusion reasoning model, and conduct a sys…

• Sumi: Open Uniform Diffusion Language Model from Scratch

  Mengyu Ye, Keito Kudo, Wataru Ikeda, Ryosuke Matsuda, Keisuke Sakaguchi, Jun Suzuki · 18 June 2026 · Language and cultural evolution

  Diffusion models have become a promising alternative to autoregressive models. Among these, uniform diffusion language models (UDLMs) permit any token to be updated at any step, in principle enabling more flexible generation. However, no UDLM has yet been pretrained from scratch at both large parame…

• The Market in the Model: Latent Diffusion as Neural Economy

  Eryk Salvaggio · 18 June 2026 · Digital Media and Philosophy

  Valuable critique of generative image models within visual culture and the humanities has emphasized the role of datasets in shaping the images they produce. Yet, close studies of the ideological positions embedded into the mechanism of the models have been neglected, leaving them imagined as "black…

• VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination

  Chunyu Liu, Zhengyang Fan, Kaisen Yang, Alex Lamb · 17 June 2026 · Large Language Models

  MDLMs generate text by denoising a preallocated masked response canvas, making response-length modeling central to instruction tuning. Existing MDLMs often inherit the autoregressive convention of using repeated \texttt{[EOS]} tokens for padding during instruction tuning, giving \texttt{[EOS]} a dua…

• Self-Generated Error Training for Token Editing in Diffusion Language Models

  Lin Yao · 17 June 2026 · Natural Language Processing Techniques

  Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference…

• LESS Is More: Mutual-Stability Sampling for Diffusion Language Models

  Amr Mohamed, Guokan Shang, Michalis Vazirgiannis · 16 June 2026 · Speech Recognition and Synthesis

  Diffusion large language models (dLLMs) offer a promising alternative to autoregressive decoding by iteratively refining masked sequences, enabling parallel token updates and bidirectional conditioning. Their practical efficiency, however, is limited by sampling procedures that execute a fixed numbe…

• HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion

  Orhun Utku Aydin, Satoru Tanioka, Tzu I Chuang, Alexander Koch, Dimitrios Rallios, Marie Gultom, Begum Tahhan, Fujimaro Ishida, Dietmar Frey, Adam Hilbert · 16 June 2026 · Intracerebral and Subarachnoid Hemorrhage Research

  Hematoma expansion (HE) after spontaneous intracerebral hemorrhage (ICH) is a major determinant of acute triage and treatment decisions in neurosurgical care. However, most existing methods provide either a binary expansion risk or a single follow-up volume, limiting uncertainty-aware decisions. We …

• Mean-Field Parallel Decoding for Discrete Diffusion Language Models

  Tamim Zoabi, Ameen Ali, Liran Ringel, Lior Wolf · 16 June 2026 · Natural Language Processing Techniques

  Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding. However, selecting tokens independently by marginal confidence limits effective parallelism: tokens that appear reliable in isolation can form incompatible configurations when several pos…

• Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel Design

  Keyue Jiang, Yuxiang Wang, Yanan Zhao, Xiang Yu, Qifang Zhao, Bohan Tang, Baojian Zhou, Yanghua Xiao, Lin Qu, Xiaoxiao Xu · 16 June 2026 · Large Language Models

  Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their performance is highly sensitive to the choice of transition kernels, and poorly designed kernels can lead to issues like training instability, slow convergence…

• Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models

  Heecheol Yun, Joonhyung Park, Joowon Kim, Eunho Yang · 16 June 2026 · Large Language Models

  Masked Diffusion Language Models (MDLMs) have emerged as a distinct paradigm for sequence generation. As MDLMs become diverse in capabilities and knowledge coverage, an important question is how to combine their knowledge. Toward this, we first investigate the unique decoding dynamics of MDLMs. We f…

• TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models

  Zhengtao Yao, Liuyang Song, Hongbo Zhang, Chenhao Wei, Haoyan Xu, Guang Yang, Siheng Wang · 12 June 2026 · Large Language Models

  Masked diffusion language models (MDLMs) such as LLaDA now rival autoregressive (AR) LLMs, but every existing knowledge-editing and unlearning method (ROME, MEMIT, etc.) targets AR transformers and either makes assumptions that fail under iterative denoising, or requires gradient updates whose backw…

• Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models

  Jia Deng, Junyi Li, Wayne Xin Zhao, Jinpeng Wang, Hongyu Lu, Ji-Rong Wen · 11 June 2026 · Large Language Models

  Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attent…

• Re-evaluating Confidence Remasking in Masked Diffusion Language Models

  Stipe Frkovic, Metod Jazbec, Dan Zhang, Christian A. Naesseth, Ilija Bogunovic, Eric Nalisnick · 11 June 2026 · Computational and Text Analysis Methods

  Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation. A notable limitation of the masked formulation, however, is that once a token has been unmasked it can no…

• Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models

  Jing Xiong, Qi Han, Shansan Gong, Yunta Hsieh, Chengyue Wu, Chaofan Tao, Chenyang Zhao, Ngai Wong · 10 June 2026 · Large Language Models

  Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with context length and becomes prohibitive for long-context scenarios. We propose Prefilling-dLLM, a training-free prefill-decode disaggregation framework for…

• Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

  Yusuf Sahin, Ahmed Rockey Saikia, Volkan Cevher, Paolo Favaro · 10 June 2026 · Generative Adversarial Networks and Image Synthesis

  Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled. Existing training-free samplers such as To…

• AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding

  Yingxuan Ren, Yuxuan Lou, Yong Liu, Pengcheng Fang, Ziming Wang, Pengfei Zhou, Yang You · 9 June 2026 · Large Language Models

  Block-wise semi-autoregressive decoding is the standard inference paradigm for diffusion large language models (DLMs), but it imposes a strict dependency between blocks: the next block cannot begin until the current block is fully decoded or its denoising budget is exhausted. We observe that once a …