English
Related papers

Related papers: DSFlow: Dual Supervision and Step-Aware Architectu…

200 papers

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yuanzhi Zhu , Hanshu Yan , Huan Yang , Kai Zhang , Junnan Li

Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Wenhao Guan , Kaidi Wang , Wangjin Zhou , Yang Wang , Feng Deng , Hui Wang , Lin Li , Qingyang Hong , Yong Qin

Diffusion probabilistic models (DPMs) have achieved impressive success in visual generation. While, they suffer from slow inference speed due to iterative sampling. Employing fewer sampling steps is an intuitive solution, but this will also…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Hu Yu , Hao Luo , Fan Wang , Feng Zhao

Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Yara Bahram , Mélodie Desbos , Mohammadhadi Shateri , Eric Granger

Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical tasks. The ReFlow procedure can accelerate sampling by…

Machine Learning · Computer Science 2024-10-11 Beomsu Kim , Yu-Guan Hsieh , Michal Klein , Marco Cuturi , Jong Chul Ye , Bahjat Kawar , James Thornton

The Distribution Matching Distillation (DMD) has been successfully applied to text-to-image diffusion models such as Stable Diffusion (SD) 1.5. However, vanilla DMD suffers from convergence difficulties on large-scale flow-based…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Xingtong Ge , Xin Zhang , Tongda Xu , Yi Zhang , Xinjie Zhang , Yan Wang , Jun Zhang

Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-24 Tianyu Cao , Helin Wang , Ari Frummer , Yuval Sieradzki , Adi Arbel , Laureano Moro Velazquez , Jesus Villalba , Oren Gal , Thomas Thebaud , Najim Dehak

Video and audio are closely correlated modalities that humans naturally perceive together. While recent advancements have enabled the generation of audio or video from text, producing both modalities simultaneously still typically relies on…

Accelerating diffusion model sampling is crucial for efficient AIGC deployment. While diffusion distillation methods -- based on distribution matching and trajectory matching -- reduce sampling to as few as one step, they fall short on…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Yihong Luo , Tianyang Hu , Jiacheng Sun , Yujun Cai , Jing Tang

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-14 Rongjie Huang , Zhou Zhao , Huadai Liu , Jinglin Liu , Chenye Cui , Yi Ren

Diffusion and flow models achieve high generative quality but remain computationally expensive due to slow multi-step sampling. Distillation methods accelerate them by training fast student generators, yet most existing objectives lack a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Yuanzhi Zhu , Eleftherios Tsonis , Lucas Degeorge , Vicky Kalogeiton

Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. However, such models are fundamentally limited by exposure bias: during inference, errors can…

Artificial Intelligence · Computer Science 2026-05-12 Wei Li , Shibo Feng , Pengcheng Wu , Xingyu Gao , Min Wu , Peilin Zhao

Diffusion models (DMs) have significantly advanced the development of real-world image super-resolution (Real-ISR), but the computational cost of multi-step diffusion models limits their application. One-step diffusion models generate…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Jianze Li , Jiezhang Cao , Yong Guo , Wenbo Li , Yulun Zhang

State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step models aim to reduce this cost by mapping noise to an image…

Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models by distilling a pretrained score network into a one- or few-step generator. While existing methods have made notable progress,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Mingyuan Zhou , Yi Gu , Zhendong Wang

Discrete diffusion or flow models could enable faster and more controllable sequence generation than autoregressive models. We show that na\"ive linear flow matching on the simplex is insufficient toward this goal since it suffers from…

Biomolecules · Quantitative Biology 2024-06-03 Hannes Stark , Bowen Jing , Chenyu Wang , Gabriele Corso , Bonnie Berger , Regina Barzilay , Tommi Jaakkola

Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. However, previous approaches typically adopt a single-stage…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Qianxin Xia , Zhiyong Shu , Wenbo Jiang , Jiawei Du , Jielei Wang , Guoming Lu

Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for…

Machine Learning · Computer Science 2026-01-21 Yuqi Li , Kuiye Ding , Chuanguang Yang , Szu-Yu Chen , Yingli Tian

Flow-based generative models achieve state-of-the-art sample quality, but require the expensive solution of a differential equation at inference time. Flow map models, commonly known as consistency models, encompass many recent efforts to…

Machine Learning · Computer Science 2025-10-07 Nicholas M. Boffi , Michael S. Albergo , Eric Vanden-Eijnden

Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient…

Machine Learning · Computer Science 2024-11-25 Xixi Hu , Bo Liu , Xingchao Liu , Qiang Liu