Search: diffusion models

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

• Unsure but Certain: Uncovering the Representation-Confidence Gap in Diffusion Language Models

  Saurabh Yadav, Badri Narayana Patro, Vijay Srinivas Agneeswaran · 11 August 2026 · Large Language Models

  Diffusion language models use broad context to create text, suggesting they might handle input noise better than standard models. Testing reveals this is only partially true. Internally, diffusion models detect text errors highly accurately. Externally, their reported certainty ignores this signal. …

• Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models

  Xuning He, Zinan Sheng, Yongding Tao, Huanyu Liu, Ge Li, Xue Jiang, Yihong Dong · 11 August 2026 · Large Language Models

  Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes them from irreversible autoregressive generation, but makes inference costly. Every denoising update alters the global context, forcin…

• Commitment Before Realization: When Classifier-Free Guidance Becomes Unnecessary in Masked Diffusion Language Models

  Fan Zhou, Weitian Wang, Tim Van de Cruys · 11 August 2026 · Language Development and Disorders

  Classifier-free guidance (CFG) is usually kept on throughout masked diffusion language model decoding, although its benefit varies across prompts and over time. We study when CFG is actually needed by comparing, from any partial output, the probability of eventual constraint satisfaction under conti…

• SDDBMs: Soft Denoising Diffusion Bridge Models

  Shiyi Qi, Kun He, Mingmou Liu · 11 August 2026 · Advanced Neuroimaging Techniques and Applications

  Diffusion bridge models leverage Doob's \(h\)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong potential in image-to-image translation and restoration. However, most existing bridge models rely on hard endpoint conditioning, which forces th…

• Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?

  Jiankun Wang, Yisen Gao, Ziwei Zhang, Xingcheng Fu, Jiaxin Bai, Chen Gao · 10 August 2026 · Multimodal Machine Learning Applications

  Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage, implicitly assuming that all available evidence should be passed to the generator. We show that this assumption does not hold for diffusion language models (DLMs): retrieving more…

• HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models

  Yu Xue, Haoxuan Qu, Zhuoling Li, Hongbin Xu, Jianxiong Yin, Simon See, Hossein Rahmani, Jun Liu · 10 August 2026 · Generative Adversarial Networks and Image Synthesis

  Training-free text-to-high-resolution image generation has recently attracted growing research attention. However, existing studies on this task primarily focus on adapting off-the-shelf U-Net-based diffusion models to high resolutions, with limited progress on adapting off-the-shelf Diffusion Trans…

• Lost in Interpolation: Why Predictive Feedback Fails in Diffusion Language Models

  Lavanya Nigam, Ishaan Bansal, Aryan Sood, Vidit Aggarwal, Gaurav Kumar Nayak · 10 August 2026 · Generative Adversarial Networks and Image Synthesis

  Soft-masking accelerates the convergence of Masked Diffusion Language Models (MDLMs). Existing formulations build this blend with linear interpolation (LERP) in the raw embedding space, which implicitly treats that space as Euclidean. We analyze the embedding space of MDLMs and find that the mask an…

• Retrofitting Linear Attention into Diffusion Language Models

  Jinha Kim, Younghun Roh, Jaeyeon Kim · 10 August 2026 · Parallel Computing and Optimization Techniques

  Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding. Recent dLLMs commonly use blockwise semi-autoregressive decoding, generating blocks autoregressively while denoising tokens within each active block in parall…

• MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models

  Tong Ling, Hang Lei, Feng Xiao, Changhui Sun, Jiahang Xie, Hao Liu, Lu Liu, Yanlong Du · 5 August 2026 · Language and cultural evolution

  Masked diffusion language models (MDLMs) enable parallel generation and bidirectional context modeling, but their positional context differs fundamentally from that of autoregressive (AR) models. Whereas AR decoding exposes a contiguous prefix, MDLM denoising produces dynamic, non-contiguous configu…

• OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models

  Xiaocheng Lu, Hualei Zhang, Shuhan Guo, Jie Zhang, Xiaoyi Pang, Jian Liu, Haoxi Li, Bohai Gu, Haoxuan Che, Jingcai Guo, Song Guo · 5 August 2026 · Large Language Models

  Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates decoding by compressing multiple teacher steps into a single student transition. However, existing methods construct supervi…

• AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

  Jiajun Liang, Yucheng Liao, Yukang Cao, Jiazhe Wei, Ken Li, Wende Tan, Jiankun Zhang, ZY Cui, Jingkang Yang, Liucheng Guo, Shiqi Yang, B. Yang, Caifeng Shan, Ziwei Liu, Chenyang Si · 4 August 2026 · Generative Adversarial Networks and Image Synthesis

  Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation still relies predominantly on discrete tokens. Existing continuous language models either inherit embedding spaces not designed for joint generatio…

• WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model

  Leyang Chen, Junyi Wu, Shaoqiu Zhang, Yulun Zhang · 4 August 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selectively update tokens, or reuse and extrapolate denoising outputs ac- cording to local drift or short native-space historie…

• Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models

  Wonseok Lee, Jimyeong Kim, Jungmin Ko, Wonjong Rhee · 4 August 2026 · Reinforcement Learning in Robotics

  Recent reinforcement learning methods for diffusion large language models (dLLMs) commonly rely on on-policy rollouts generated by the target dLLM itself. When successful on-policy rollouts are scarce, however, on-policy training may receive little positive reward and make only limited progress. To …

• Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

  Jinyuan Liu, Tianshuo Cong, Pei Li, Tianrui Wang, Xinlei He, Anyu Wang, Xiaoyun Wang · 4 August 2026 · Advanced Steganography and Watermarking Techniques

  Although semantic watermarking is considered a promising safeguard for images generated by Latent Diffusion Models (LDMs), the reliance of the watermark detection pipeline on neural networks introduces a critical yet underexplored backdoor attack surface. To systematically study this vulnerability, …

• DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis

  Wasim Madha, Nityanand Mathur, Hamees Sayed, Apoorv Singh, Sameer Khurana, Akshat Mandloi, Sudarshan Kamath · 4 August 2026 · Speech Recognition and Synthesis

  Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We prese…

• EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change Captioning

  Dongwei Sun, Bowen Yao, Yujie Zhang, Pei Liu, Jing Yao, Xiangyong Cao · 4 August 2026 · Remote-Sensing Image Classification

  Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions. However, existing change captioning methods always follow an autoregressive decodi…

• REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models

  Xiang Xia, Cheng Yan, Yiming Zhang, Jiazheng Liu, Hongyu Zhang, Wuyang Zhang · 4 August 2026 · Mobile Crowdsensing and Crowdsourcing

  Mixture-of-experts (MoE) models increase parameter capacity by activating only a small subset of experts for each token. This conditional-computation paradigm has enabled autoregressive language models to scale model capacity without a proportional increase in per-token computation. In diffusion lan…

• Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models

  Yaoxuan Dou, Yang Shu · 3 August 2026 · Neurobiology of Language and Bilingualism

  Training-free acceleration makes diffusion-based multimodal large language models (dMLLMs) more deployable, but it may silently change generated content. We study this serving-time consistency problem on 300 real images, comparing Fast-dLLM outputs with the same model's unaccelerated outputs. Across…

• Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models

  Chia-Ming Lee, Shao-Kai Liu, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu · 31 July 2026 · Large Language Models

  Diffusion language models expose a provisional prediction at every denoising step, and on many tasks the candidate answer inside it stabilizes before the step schedule is exhausted. This creates two acceleration opportunities, leaving a block early and stopping the sequence early, but the two requir…

• Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model

  Carlos Mu\~noz-Romero, Jose A. Gonzalez-Lopez · 30 July 2026 · Face recognition and analysis

  Zero-shot text-to-speech (TTS) clones a voice from a short audio prompt, but this reliance on reference audio is a barrier when only visual information is available, e.g. for historical figures or video-game characters. In this work, we propose a Face-to-Speech (F2S) framework that predicts a plausi…

• Diffusion Disambiguation Models for Partial Label Learning

  Jinfu Fan, Xiaohui Zhong, Kangrui Ren, Jiangnan Li, Linqing Huang, Min Gan, C. L. Philip Chen · 29 July 2026 · Machine Learning and Data Classification

  Learning from ambiguous labels is a long-standing problem in practical machine learning applications. The purpose of \emph{partial label learning} (PLL) is to identify the ground-truth label from a set of candidate labels associated with a given instance. Inspired by the remarkable performance of di…

• Neuromorphic Diffusion Language Models: Addressing Compute and Memory Bottlenecks via Sparsity and Block Denoising

  Dengyu Wu, Clement Ruah, Jiechen Chen, Bipin Rajendran, Osvaldo Simeone · 29 July 2026 · Advanced Memory and Neural Computing

  Autoregressive (AR) large language models (LLMs) are inherently inefficient at inference time because each generated token requires accessing the full set of model parameters, leading to low operational intensity and high energy consumption. Masked diffusion language models (MDLMs) partially address…

• Diffusion Model-based Parameter Estimation in Dynamic Power Systems

  Feiqin Zhu, Dmitrii Torbunov, Zhongjing Jiang, Tianqiao Zhao, Amirthagunaraj Yogarathnam, Yihui Ren, Meng Yue · 29 July 2026 · Power System Optimization and Stability

  Parameter estimation, which represents a classical inverse problem, is often ill-posed as different parameter combinations can yield identical outputs. This non-uniqueness presents a critical barrier to accurate and unique identification. Here we introduce a parameter estimation framework to address…

• PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention

  Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Jesson Wang, Siheng Wang, Guang Yang, Haoyan Xu, Chenhao Wei, Zhengqing Yuan, Youran Shen, Yanfang Ye, Junhao Dong · 29 July 2026 · Generative Adversarial Networks and Image Synthesis

  Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising. We study this problem at the level of attention rather than claiming AR-weight reus…

• CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models

  Yash Shah, Abhijit Chakraborty, Vivek Gupta · 29 July 2026 · Large Language Models

  Masked diffusion language models (MDLMs) are advancing rapidly, yet the evaluation standards needed to reliably interpret their progress have not kept pace. Despite MDLMs becoming competitive with autoregressive language models, seven recent remasking papers evaluate under incompatible settings, var…