English
Related papers

Related papers: DITTO: Diffusion Inference-Time T-Optimization for…

200 papers

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yuang Ai , Qihang Fan , Xuefeng Hu , Zhenheng Yang , Ran He , Huaibo Huang

Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like Stable Diffusion. However, their widespread use also poses potential privacy risks. A key concern…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Guo Li , Weihong Chen , Yongfu Fan

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Computation and Language · Computer Science 2023-05-09 Zecheng Tang , Pinzheng Wang , Keyan Zhou , Juntao Li , Ziqiang Cao , Min Zhang

Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both…

Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes, resulting in inadequate fitting of rare or never-used notes and thus reducing the diversity of generated samples. We argue…

Sound · Computer Science 2024-08-06 Shipei Liu , Xiaoya Fan , Guowei Wu

Music mastering style transfer aims to model and apply the mastering characteristics of a reference track to a target track, simulating the professional mastering process. However, existing methods apply fixed processing based on a…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the…

Sound · Computer Science 2024-10-31 Javier Nistal , Marco Pasini , Stefan Lattner

The quality of the text-to-music models has reached new heights due to recent advancements in diffusion models. The controllability of various musical aspects, however, has barely been explored. In this paper, we propose Mustango: a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-18 Jan Melechovsky , Zixun Guo , Deepanway Ghosal , Navonil Majumder , Dorien Herremans , Soujanya Poria

Without using explicit reward, direct preference optimization (DPO) employs paired human preference data to fine-tune generative models, a method that has garnered considerable attention in large language models (LLMs). However, exploration…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xierui Wang , Xiaoyin Xu , Min Zhang

In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Such datasets are expected to cover various driving scenarios…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Jiahang Tu , Wei Ji , Hanbin Zhao , Chao Zhang , Roger Zimmermann , Hui Qian

Diffusion models are the mainstream approach for time series generation tasks. However, existing diffusion models for time series generation require retraining the entire framework to introduce specific conditional guidance. There also…

Machine Learning · Computer Science 2025-09-25 Mingchun Sun , Rongqiang Zhao , Hengrui Hu , Songyu Ding , Jie Liu

Deep generative models are now able to synthesize high-quality audio signals, shifting the critical aspect in their development from audio quality to control capabilities. Although text-to-music generation is getting largely adopted by the…

Sound · Computer Science 2024-08-02 Nils Demerlé , Philippe Esling , Guillaume Doras , David Genova

Songs, as a central form of musical art, exemplify the richness of human intelligence and creativity. While recent advances in generative modeling have enabled notable progress in long-form song generation, current systems for full-length…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-25 Huakang Chen , Yuepeng Jiang , Guobin Ma , Chunbo Hao , Shuai Wang , Jixun Yao , Ziqian Ning , Meng Meng , Jian Luan , Lei Xie

This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities,…

Artificial Intelligence · Computer Science 2025-01-22 Masatoshi Uehara , Yulai Zhao , Chenyu Wang , Xiner Li , Aviv Regev , Sergey Levine , Tommaso Biancalani

We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise…

Sound · Computer Science 2026-01-29 Ching Ho Lee , Javier Nistal , Stefan Lattner , Marco Pasini , George Fazekas

We introduce EzAudio, a text-to-audio (T2A) generation framework designed to produce high-quality, natural-sounding sound effects. Core designs include: (1) We propose EzAudio-DiT, an optimized Diffusion Transformer (DiT) designed for audio…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-23 Jiarui Hai , Yong Xu , Hao Zhang , Chenxing Li , Helin Wang , Mounya Elhilali , Dong Yu

The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Mihir Prabhudesai , Tsung-Wei Ke , Alexander C. Li , Deepak Pathak , Katerina Fragkiadaki

This paper explores advancements in high-fidelity personalized image generation through the utilization of pre-trained text-to-image diffusion models. While previous approaches have made significant strides in generating versatile scenes…

Computer Vision and Pattern Recognition · Computer Science 2023-12-04 Zhonghao Wang , Wei Wei , Yang Zhao , Zhisheng Xiao , Mark Hasegawa-Johnson , Humphrey Shi , Tingbo Hou

Text-to-music generation models are now capable of generating high-quality music audio in broad styles. However, text control is primarily suitable for the manipulation of global musical attributes like genre, mood, and tempo, and is less…

Sound · Computer Science 2023-11-14 Shih-Lun Wu , Chris Donahue , Shinji Watanabe , Nicholas J. Bryan