Search: diffusion models

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

• SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching

  Zhendong Mi, Pu Zhao, Ziyu Hu, Xiaodong Yu, Yanzhi Wang, Grace Li Zhang, Shaoyi Huang · 5 October 2026 · Caching and Content Delivery

  Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Transformer evaluations during denoising. Existing caching methods mainly exploit temporal redundancy at the feature or token level, leaving the underlyi…

• FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

  Darshan Thaker, Lachlan Ewen MacDonald, Ren\'e Vidal · 1 October 2026 · Generative Adversarial Networks and Image Synthesis

  Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time. However, its computational cost remains high as each decoding iteration incurs expensive diffusion model forward passes and reward model backpropagati…

• Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails

  Gert Lek, Abele Malan, Chaoyi Zhu, Pin-Yu Chen, Robert Birke, Lydia Chen · 29 September 2026 · Transportation Safety and Impact Analysis

  Guard models are the last line of defense between a language model and a harmful output, yet their training objective is surprisingly narrow. Existing guards learn to predict a single verdict token from a conversational context, concentrating supervision on a single target. The consequences are stru…

• Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models

  Xiaoyi Yu, Enver Sangineto, Pei Fu, Fiorenzo Parascandolo, Wenhui Tan, Ruikang Zhang, Rita Cucchiara, Ruihua Song, Jian Luan · 23 September 2026 · Large Language Models

  Diffusion Large Language Models (dLLMs) have emerged as an efficient alternative to autoregressive models, yet aligning them via Reinforcement Learning (RL) requires likelihood surrogates estimated from masked reconstruction subproblems under a small Monte Carlo budget per rollout. Existing methods …

• Exploring the Potential of Diffusion Large Language Models in Code Generation

  Chengze Li, Yitong Zhang, Jia Li, Liyi Cai, Ge Li · 16 September 2026 · Natural Language Processing Techniques

  LLMs have become the mainstream approaches to code generation. Existing LLMs mainly employ autoregressive generation, i.e. generating code token-by-token from left to right. However, the underlying autoregressive generation has two limitations in code generation. First, autoregressive LLMs only gene…

• Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image Generators

  Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger, Daniel Panangian, Ksenia Bittner, Konrad Schindler · 11 September 2026 · Advanced Image Processing Techniques

  High-resolution digital surface models (DSMs) play an important role in urban analysis, 3D building reconstruction, and infrastructure monitoring, yet their availability remains limited due to the high cost and complexity of data acquisition. In contrast, coarse DSMs from commercial satellite missio…

• Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference

  Wooje Park, Insu Lee, Minyoung Noh, Jaeyun Jang, Sungmin Lee, Kyuhong Shim, Byonghyo Shim · 28 August 2026 · Large Language Models

  Diffusion large language models (dLLMs) offer a promising alternative to autoregressive generation by decoding multiple tokens in parallel through iterative denoising. However, increasing decoding parallelism often degrades generation quality, as early errors can contaminate later contexts. Revocabl…

• Affix Cache for Diffusion Large Language Models

  Kaihua Liang, An Zhong, Xin Tan, Zafar Ayyub Qazi, Hong Xu, Jian Weng, Marco Canini · 28 August 2026 · Caching and Content Delivery

  Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding and bidirectional context modeling, but efficient inference remains challenging. Unlike autoregressive systems, whose key-value (KV) cache can be reused for shared prefixes, DLLMs couple the KV states of shared context tokens…

• Multiphase-Diff: Diffusion-Based Generative Modeling for High-Contrast Multiphase Physical Systems with Sharp Interfaces

  Yining Huang, Zhenyu Liang · 17 August 2026 · Solidification and crystal growth phenomena

  Physics-constrained diffusion for high-contrast, sharp-interface multiphase fields faces three coupled difficulties. At coefficient jumps, expanded pointwise strong-form PDE residuals contain singular gradient terms that can penalize physical interfaces. Under extreme contrast, low-magnitude phases …

• Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models

  Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Bo Han, Ivor Tsang, Yanfeng Wang, Bo Zheng, Jiangchao Yao · 13 August 2026 · Large Language Models

  Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-positi…

• Progressive Learning of a Diffusion-based Inpainting Model for Separating Overlapped Fingerprints

  Noor Hussein, Anil K. Jain, Karthik Nandakumar · 5 August 2026 · Biometric Identification and Security

  Overlapped friction ridge patterns are a recurring problem in latent fingerprints recovered from crime scenes and in live-scan scenarios where residual fingerprints on the sensor may corrupt subsequent acquisitions. Existing approaches for separating overlapped fingerprints either rely on rule-based…

• Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models

  Xingyu Mou, Zijin Huang, Tianze Zhang, Yuxin Ma, Lanning Wei, Zengfeng Huang, Da Zheng, Lun Du · 30 July 2026 · Natural Language Processing Techniques

  Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping quadratic attention costs tractable. Yet blockwise generation creates a structural weakness: tokens near a block boundary lack future cross-b…

• UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

  Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, Pipi Hu · 28 July 2026 · Generative Adversarial Networks and Image Synthesis

  Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remains editable during sampling. However, adapting AR checkpoints across corruption kernels remains challenging because exis…

• LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models

  Xingru Chen, Zelang Liang, Yongjia Ma, Jiqing Zhan, Shuling Yang, Lian Wen, Kun Zhan · 21 July 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion-based Large Language Models(DLLMs) enable parallel generation via Semi-Autoregressive (SAR) decoding in text generation. However, current methods suffer from severe operator-level redundancy: they recompute the entire sequence during denoising steps, ignoring that the prefix and masked suf…

• Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques

  Daehoon Gwak, Minhyung Lee, Junwoo Park, Jaegul Choo · 15 July 2026 · Advanced Neural Network Applications

  Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guarantee practical speedups. Realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware cac…

• Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

  Sterling Huang, Abigayle Brown, Jiyoo Noh, Jiakang Xu, Wantong Huo, Kaung Myat Kyaw, Jonathan Chan · 14 July 2026 · Generative Adversarial Networks and Image Synthesis

  Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines whether LLMLingua-2 transfers effectively to diffusion large language models (DLLMs), specifically LLaDA-8B-Instruct. We eval…

• Don't Commit Alone: Joint Token Commitment in Diffusion Large Language Models

  Lin Yao · 7 July 2026 · Large Language Models

  Diffusion large language models (dLLMs) commit multiple tokens per denoising step by decoding each selected position independently from the shared context; when those positions are dependent, the resulting factorization error is captured by conditional total correlation, which confidence-based selec…

• Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{\"o}dinger bridge

  Titouan Vayer (COMPACT) · 30 June 2026 · Slime Mold and Myxomycetes Research

  These notes recapitulate the high level mathematical principles behind different techniques for generative modeling. I show the connections between optimal transport and standard techniques such as Schr{\"o}dinger bridge and flow matching.…

• Understanding Evaluation Illusion in Diffusion Large Language Models

  Hengxiang Zhang, Jiaxi Ren, Hongxin Wei · 30 June 2026 · Large Language Models

  Despite the capability of parallel decoding, diffusion large language models (dLLMs) require many denoising steps to maintain generation quality, motivating recent research on efficient decoding strategies. However, existing studies have reported inconsistent evaluation results even under seemingly …

• Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?

  Mikel N. Legasa, Antoine Doury, Achille Gellens, Redouane Lguensat, Clara Naldesi, Soulivanh Thao, Mathieu Vrac · 15 June 2026 · Climate variability and models

  Emulators provide a cost-effective alternative to regional climate models (RCMs) by capturing their dynamical downscaling function. They link large-scale predictors simulated by global climate models (GCMs) to RCM-simulated high-resolution fields of the target variable, here precipitation. Machine l…

• DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation

  Kangning Zhang, Yingjie Qin, Weinan Zhang, Yong Yu, Jianghao Lin · 11 June 2026 · Recommender Systems and Techniques

  Cold-start item recommendation remains a persistent challenge in real-world systems due to the absence of interaction histories. While prior models attempt to bridge this gap using item content features, they universally suffer from the \textbf{seesaw dilemma}: enhancing performance for cold items i…

• Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models

  Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Hongchen Luo, Xueyang Fu, Yang Cao, Wei Zhai, Zheng-Jun Zha · 9 June 2026 · Large Language Models

  Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward mis…

• FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

  Haoyu Huang, Linlin Yang, Sheng Xu, Boyu Liu, Guodong Guo, Zhongqian Fu, Hang Zhou, Baochang Zhang · 8 June 2026 · Large Language Models

  Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written. We reveal that Post-Training Quantization (PTQ) error easily flips these borderline decisions at the write front…

• SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding

  Na Li, Chengda Wang, Mingju Gao, Hao Tang · 4 June 2026 · Generative Adversarial Networks and Image Synthesis

  Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quali…

• UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation

  Zeyuan Yang, Hao-Wei Chen, Xueyang Yu, Yuncong Yang, Haoyu Zhen, Ziqiao Ma, Maohao Shen, Chuang Gan · 4 June 2026 · Generative Adversarial Networks and Image Synthesis

  Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single architecture. While autoregressive VLMs can reason across modalities, they fail to generate high-quality images. In contrast, diffusion models produce ph…