English
Related papers

Related papers: $Z^2$-Sampling: Zero-Cost Zigzag Trajectories for …

200 papers

Diffusion models, the most popular generative paradigm so far, can inject conditional information into the generation path to guide the latent towards desired directions. However, existing text-to-image diffusion models often fail to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Lichen Bai , Shitong Shao , Zikai Zhou , Zipeng Qi , Zhiqiang Xu , Haoyi Xiong , Zeke Xie

Diffusion models generate conditional samples by progressively denoising Gaussian noise, yet the denoising trajectory can stall at visually plausible but low-quality outcomes with conditional misalignment or structural artifacts. We…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Shunqi Mao , Wei Guo , Chaoyi Zhang , Jieting Long , Ke Xie , Weidong Cai

Whereas the ability of deep networks to produce useful predictions has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approaches such as MC-Dropout and Deep Ensembles have emerged as…

Machine Learning · Computer Science 2024-05-28 Nikita Durasov , Nik Dorndorf , Hieu Le , Pascal Fua

We introduce the use of the Zig-Zag sampler to the problem of sampling conditional diffusion processes (diffusion bridges). The Zig-Zag sampler is a rejection-free sampling scheme based on a non-reversible continuous piecewise deterministic…

Statistics Theory · Mathematics 2024-09-04 Joris Bierkens , Sebastiano Grazzi , Frank van der Meulen , Moritz Schauer

Standard MCMC methods can scale poorly to big data settings due to the need to evaluate the likelihood at each iteration. There have been a number of approximate MCMC algorithms that use sub-sampling ideas to reduce this computational…

Computation · Statistics 2020-09-29 Joris Bierkens , Paul Fearnhead , Gareth Roberts

Text-to-image generation models have made significant progress in producing high-quality images from textual descriptions, yet they continue to struggle with maintaining subject consistency across multiple images, a fundamental requirement…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Mingxiao Li , Mang Ning , Marie-Francine Moens

Piecewise deterministic Markov processes provide scalable methods for sampling from the posterior distributions in big data settings by admitting principled sub-sampling strategies that do not bias the output. An important example is the…

Computation · Statistics 2025-08-04 Sanket Agrawal , Joris Bierkens , Gareth O. Roberts

Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free Guidance (CFG). However, despite its pivotal role in aligning generated content with…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Haosen Li , Wenshuo Chen , Lei Wang , Shaofeng Liang , Bowen Tian , Soning Lai , Yutao Yue

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Vincent Tao Hu , Stefan Andreas Baumann , Ming Gui , Olga Grebenkova , Pingchuan Ma , Johannes Schusterbauer , Björn Ommer

Diffusion models have emerged as powerful generative techniques for solving inverse problems. Despite their success in a variety of inverse problems in imaging, these models require many steps to converge, leading to slow inference time.…

Image and Video Processing · Electrical Eng. & Systems 2024-11-13 Yaşar Utku Alçalar , Mehmet Akçakaya

Incorporating a temporal dimension into pretrained image diffusion models for video generation is a prevalent approach. However, this method is computationally demanding and necessitates large-scale video datasets. More critically, the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Dengsheng Chen , Jie Hu , Xiaoming Wei , Enhua Wu

We construct a zig-zag process targeting a posterior distribution defined on a hybrid state space consisting of both discrete and continuous variables. The construction does not require any assumptions on the structure among discrete…

Computation · Statistics 2024-01-30 Jere Koskela

State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing PointMamba-based…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Linshuang Diao , Sensen Song , Yurong Qian , Dayong Ren

Diffusion models have recently demonstrated an impressive ability to address inverse problems in an unsupervised manner. While existing methods primarily focus on modifying the posterior sampling process, the potential of the forward…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Gongye Liu , Haoze Sun , Jiayi Li , Fei Yin , Yujiu Yang

Diffusion models often exhibit inconsistent sample quality due to stochastic variations inherent in their sampling trajectories. Although training-based fine-tuning (e.g. DDPO [1]) and inference-time alignment techniques[2] aim to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Sixian Wang , Zhiwei Tang , Tsung-Hui Chang

The generation of high-quality, diverse, and prompt-aligned images is a central goal in image-generating diffusion models. The popular classifier-free guidance (CFG) approach improves quality and alignment at the cost of reduced variation,…

Machine Learning · Computer Science 2025-10-21 Enhao Gu , Haolin Hou

Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a…

Machine Learning · Computer Science 2024-08-06 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

Image generation using diffusion models have demonstrated outstanding learning capabilities, effectively capturing the full distribution of the training dataset. They are known to generate wide variations in sampled images, albeit with a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Rahul Shenoy , Zhihong Pan , Kaushik Balakrishnan , Qisen Cheng , Yongmoon Jeon , Heejune Yang , Jaewon Kim

Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these images failing to align closely with the given text prompts. Classifier-free guidance (CFG)…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Zhenyu Zhou , Defang Chen , Can Wang , Chun Chen , Siwei Lyu

We introduce Wedge Sampling, a new non-adaptive sampling scheme for low-rank tensor completion. We study recovery of an order-$k$ low-rank tensor of dimension $n \times \cdots \times n$ from a subset of its entries. Unlike the standard…

Machine Learning · Statistics 2026-02-06 Hengrui Luo , Anna Ma , Ludovic Stephan , Yizhe Zhu
‹ Prev 1 2 3 10 Next ›