English
Related papers

Related papers: Decoupling Complexity from Scale in Latent Diffusi…

200 papers

Diffusion models (DMs) have revolutionized image generation, producing high-quality images with applications spanning various fields. However, their ability to create hyper-realistic images poses significant challenges in distinguishing…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Santosh , Li Lin , Irene Amerini , Xin Wang , Shu Hu

Image generation models trained on large datasets can synthesize high-quality images but often produce spatially inconsistent and distorted images due to limited information about the underlying structures and spatial layouts. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Hyundo Lee , Suhyung Choi , Inwoo Hwang , Byoung-Tak Zhang

In the medical domain, acquiring large datasets is challenging due to both accessibility issues and stringent privacy regulations. Consequently, data availability and privacy protection are major obstacles to applying machine learning in…

Image and Video Processing · Electrical Eng. & Systems 2025-07-02 Wenwu Tang , Khaled Seyam , Bin Yang

Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Jason Becker , Chris Wendler , Peter Baylies , Robert West , Christian Wressnegger

Generative diffusion models have achieved remarkable success in producing high-quality images. However, these models typically operate in continuous intensity spaces, diffusing independently across pixels and color channels. As a result,…

Graphics · Computer Science 2025-05-20 Javier E. Santos , Agnese Marcato , Roman Colman , Nicholas Lubbers , Yen Ting Lin

Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…

Computation and Language · Computer Science 2026-01-06 Viacheslav Meshchaninov , Egor Chimbulatov , Alexander Shabalin , Aleksandr Abramov , Dmitry Vetrov

Recent studies in extreme image compression have achieved remarkable performance by compressing the tokens from generative tokenizers. However, these methods often prioritize clustering common semantics within the dataset, while overlooking…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Naifu Xue , Zhaoyang Jia , Jiahao Li , Bin Li , Yuan Zhang , Yan Lu

Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind…

Computation and Language · Computer Science 2025-07-04 Chengyue Wu , Hao Zhang , Shuchen Xue , Zhijian Liu , Shizhe Diao , Ligeng Zhu , Ping Luo , Song Han , Enze Xie

Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos. A natural next step toward a single architecture for both generation (visual synthesis) and understanding…

Computation and Language · Computer Science 2026-05-11 Jiaxiu Jiang , Jingjing Ren , Wenbo Li , Bo Wang , Haoze Sun , Yijun Yang , Jianhui Liu , Yanbing Zhang , Shenghe Zheng , Yuan Zhang , Haoyang Huang , Nan Duan , Wangmeng Zuo

Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown comparable performance by…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Kihong Kim , Haneol Lee , Jihye Park , Seyeon Kim , Kwanghee Lee , Seungryong Kim , Jaejun Yoo

Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts describing complex scenes with multiple objects. While excelling in…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Hanan Gani , Shariq Farooq Bhat , Muzammal Naseer , Salman Khan , Peter Wonka

Lidar point cloud synthesis based on generative models offers a promising solution to augment deep learning pipelines, particularly when real-world data is scarce or lacks diversity. By enabling flexible object manipulation, this synthesis…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Zhengkang Xiang , Zizhao Li , Amir Khodabandeh , Kourosh Khoshelham

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Artificial Intelligence · Computer Science 2026-04-14 Haomin Zuo , Yidi Li , Luoxiao Yang , Xiaofeng Zhang

Significant advancements have been achieved in the realm of large-scale pre-trained text-to-video Diffusion Models (VDMs). However, previous methods either rely solely on pixel-based VDMs, which come with high computational costs, or on…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 David Junhao Zhang , Jay Zhangjie Wu , Jia-Wei Liu , Rui Zhao , Lingmin Ran , Yuchao Gu , Difei Gao , Mike Zheng Shou

Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities remains challenging. Existing approaches often rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Xiangyi Chen , Théophane Vallaeys , Maha Elbayad , John Nguyen , Jakob Verbeek

We demonstrate the capabilities of probabilistic diffusion models to reduce dramatically the computational cost of expensive hydrodynamical simulations to study the relationship between observable baryonic cosmological probes and dark…

Cosmology and Nongalactic Astrophysics · Physics 2026-01-22 Satvik Mishra , Roberto Trotta , Matteo Viel

Recent advances in text-to-image diffusion models have demonstrated impressive capabilities in image quality. However, complex scene generation remains relatively unexplored, and even the definition of `complex scene' itself remains…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Minghao Liu , Le Zhang , Yingjie Tian , Xiaochao Qu , Luoqi Liu , Ting Liu

Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Dejia Xu , Hanwen Liang , Neel P. Bhatt , Hezhen Hu , Hanxue Liang , Konstantinos N. Plataniotis , Zhangyang Wang

Recent advancements in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis. However, synthetic data…

Machine Learning · Computer Science 2025-06-11 Ying Zhou , Xinyao Wang , Yulei Niu , Yaojie Shen , Lexin Tang , Fan Chen , Ben He , Le Sun , Longyin Wen

Latent diffusion models (LDMs) have demonstrated remarkable generative capabilities across various low-level vision tasks. However, their potential for point cloud completion remains underexplored due to the unstructured and irregular…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zijun Li , Hongyu Yan , Shijie Li , Kunming Luo , Li Lu , Xulei Yang , Weisi Lin