English
Related papers

Related papers: ToDo: Token Downsampling for Efficient Generation …

200 papers

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Artificial Intelligence · Computer Science 2024-08-21 Chunting Zhou , Lili Yu , Arun Babu , Kushal Tirumala , Michihiro Yasunaga , Leonid Shamis , Jacob Kahn , Xuezhe Ma , Luke Zettlemoyer , Omer Levy

Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Yupei Lin , Sen Zhang , Xiaojun Yang , Xiao Wang , Yukai Shi

Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images but typically suffer from inefficient sampling. Many solver designs and noise scheduling strategies have been proposed to dramatically improve…

Machine Learning · Statistics 2025-10-01 Tianrong Chen , Huangjie Zheng , David Berthelot , Jiatao Gu , Josh Susskind , Shuangfei Zhai

Autoregressive models with continuous tokens form a promising paradigm for visual generation, especially for text-to-image (T2I) synthesis, but they suffer from high computational cost. We study how to design compute-efficient linear…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Jiahao Wang , Ting Pan , Haoge Deng , Dongchen Han , Taiqiang Wu , Xinlong Wang , Ping Luo

Text-to-image diffusion models often exhibit degraded performance when generating images beyond their training resolution. Recent training-free methods can mitigate this limitation, but they often require substantial computation or are…

Machine Learning · Computer Science 2025-10-31 Sungho Koh , SeungJu Cha , Hyunwoo Oh , Kwanyoung Lee , Dong-Jin Kim

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Theodoros Kouzelis , Efstathios Karypidis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

In recent advancements in high-fidelity image generation, Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a key player. However, their application at high resolutions presents significant computational challenges. Current…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Jing Nathan Yan , Jiatao Gu , Alexander M. Rush

Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Xiang Chen , Hao Li , Mingqiang Li , Jinshan Pan

Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality images by mapping noise to a data distribution. However, recent findings suggest that image likelihood does not align with perceptual…

Machine Learning · Computer Science 2025-05-29 Rafał Karczewski , Markus Heinonen , Vikas Garg

Recent training-free layout-to-image diffusion models have demonstrated remarkable performance in generating high-quality images with controllable layouts. These models follow a one-stage framework: Encouraging the model to focus the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Linhao Huang , Jing Yu

Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Zhentao Fan , Hongming Chen , Yufeng Li

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yifei Liu , Mathias Gehrig , Nico Messikommer , Marco Cannici , Davide Scaramuzza

Recent advancements in diffusion models have introduced fast sampling methods that can effectively produce high-quality images in just one or a few denoising steps. Interestingly, when these are distilled from existing diffusion models,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Rinon Gal , Or Lichter , Elad Richardson , Or Patashnik , Amit H. Bermano , Gal Chechik , Daniel Cohen-Or

Despite many attempts to leverage pre-trained text-to-image models (T2I) like Stable Diffusion (SD) for controllable image editing, producing good predictable results remains a challenge. Previous approaches have focused on either…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Sherry X. Chen , Yaron Vaxman , Elad Ben Baruch , David Asulin , Aviad Moreshet , Kuo-Chin Lien , Misha Sra , Pradeep Sen

Entrusted with the goal of pixel-level object classification, the semantic segmentation networks entail the laborious preparation of pixel-level annotation masks. To obtain pixel-level annotation masks for a given class without human…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Joon Hyun Park , Kumju Jo , Sungyong Baik

Text-to-image (T2I) generation with Stable Diffusion models (SDMs) involves high computing demands due to billion-scale parameters. To enhance efficiency, recent studies have reduced sampling steps and applied network quantization while…

Machine Learning · Computer Science 2024-12-03 Bo-Kyeong Kim , Hyoung-Kyu Song , Thibault Castells , Shinkook Choi

Text-to-image diffusion models can create stunning images from natural language descriptions that rival the work of professional artists and photographers. However, these models are large, with complex network architectures and tens of…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Yanyu Li , Huan Wang , Qing Jin , Ju Hu , Pavlo Chemerys , Yun Fu , Yanzhi Wang , Sergey Tulyakov , Jian Ren