扩散模型先验知识赋能人物搜索新范式，精准提升行人重识别效果
arXiv:2510.01841v2 Announce Type: replace Abstract: Person search aims to jointly perform person detection and re-identification by localizing and ide…
扩散模型助力数字乳腺断层合成，解决有限角度重建难题，突破98%未测量空间限制
arXiv:2607.12937v1 Announce Type: cross Abstract: Limited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose projectio…
用张量列低秩分解攻克扩散模型高维采样难题，带来理论与计算效率双重飞跃。
arXiv:2607.06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learn…
扩散模型遇瓶颈？SE-UNet用奇等变框架解决真实世界逆问题中的物理约束难题
arXiv:2607.02628v1 Announce Type: cross Abstract: While diffusion models have revolutionized image synthesis, their application to real-world inverse …
扩散与流模型的黑盒对齐新方法，信任区域噪声搜索带来高效微调
arXiv:2603.14504v2 Announce Type: replace-cross Abstract: Optimizing the noise samples of diffusion and flow models is an increasingly popular approac…
医学MRI重建新突破：高维嵌入先验巧解噪声K空间恢复难题，扩散模型再显神通
arXiv:2607.01176v1 Announce Type: new Abstract: Magnetic resonance imaging (MRI) reconstruction under realistic acquisition conditions can be fundamen…
用引导补丁扩散模型，从单张无滤波器灰度快照重建高光谱图像，开创低成本计算成像新思路
arXiv:2412.02798v3 Announce Type: replace Abstract: We consider the problem of reconstructing a HxWx31 hyperspectral image from a $H\times W$ grayscal…
全新3D区域感知扩散模型，精准修复脑部MRI纵向病灶，消除神经影像分析偏差
arXiv:2603.05693v2 Announce Type: replace-cross Abstract: Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bia…
用扩散模型生成与音乐同步的AI编舞，舞蹈练习的颠覆性新工具来了。
arXiv:2606.26507v1 Announce Type: cross Abstract: In recent years, advancements in deep learning and generative models have revolutionized music-drive…
探索扩散模型中内生思维链推理新机制，突破MLLM文本编码器的推理瓶颈。
arXiv:2603.12252v4 Announce Type: replace-cross Abstract: Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusio…
挑战扩散模型主流地位，快速U-Net实现配对医学图像翻译，兼顾速度与质量。
arXiv:2606.17675v1 Announce Type: new Abstract: Magnetic resonance imaging-signal fat fraction (MRI-SFF) quantifies tissue fat and serves as an establ…
统一多模态潜在扩散模型实现任意模态间的连贯生成，无需配对数据，跨模态生成能力惊艳
arXiv:2606.16408v1 Announce Type: new Abstract: We introduce MUNI, an end-to-end multimodal latent diffusion framework for any-to-any generation that …
扩散模型推理还能更省？预算约束下的步骤级缓存策略，为生成式AI降本增效提供新思路。
arXiv:2606.13496v1 Announce Type: new Abstract: Step-level caching accelerates diffusion models by exploiting temporal redundancy across denoising ste…
访问arXiv论文库中的最新技术报告，快速获取扩散模型从左到右生成的前沿研究，学术必备
arXiv:2606.11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their …
基于文本扩散的开放AI模型，本地推理速度提升4倍，高效处理文本生成任务
IT之家 6 月 11 日消息，谷歌今天（6 月 11 日）发布公告，宣布推出 DiffusionGemma，是基于文本扩散机制的开放 AI 模型， 相比较自回归模型在本地推理速度上提升了 4 倍。 IT之家注：自回归模型（Autoregressive Model）是当前主流的大语言模型架构（如 G…
视频扩散模型新突破：细粒度稀疏注意力FG-Attn，大幅提升计算效率与生成质量。
arXiv:2509.16518v2 Announce Type: replace Abstract: Using diffusion transformers for media generation may require evaluating attention over extremely …
提出重叠小波扩散模型，巧用频域分解提升低光图像增强效果与细节保留。
arXiv:2606.10280v1 Announce Type: cross Abstract: In this study, we propose an overlapped wavelet diffusion framework for Low-Light Image Enhancement …
揭秘掩码扩散语言模型并行解码的脆弱性，提出关注度折扣自适应采样器提升效率与安全。
arXiv:2606.10829v1 Announce Type: cross Abstract: Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoisi…