One-Step Generative Modeling

Follow this topic Ask about this topic

Momentum

16 papers in the last four weeks, against 1 the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 97

All topics

TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
Apr 16, 2026Xiangyu Liu, Feng Gao, Xiaomei Zhang +4Audio-Video Generation Video Diffusion Models
1MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · 3Meituan +2
Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
Mar 30, 2026Zhen Zou, Xiaoxiao Ma, Mingde Yao +3Autoregressive Diffusion Visual Autoregressive Models
University of Science and Technology of China · The Chinese University of Hong Kong, MMLAB · JD Explore Academy +1
Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation
Mar 12, 2026Chongyang Xu, Yixian Zou, Tianyu Yang +4Robot Policy Learning Robot Skill Learning
College of Computer Science, Sichuan University, Chengdu, China · School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
Manifold-Aligned Generative Transport
Feb 23, 2026Xinyu Tian, Xiaotong ShenOne-Step Generative Modeling Generative Modeling
School of Statistics, University of Minnesota, MN, 55455 USA
Dual-End Consistency Model
Feb 11, 2026Linwei Dong, Ruoyu Guo, Ge Bai +3One-Step Generative Modeling Consistency Distillation
1Zhejiang University · 2Bytedance Inc. · 3Zhejiang Lab
SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
Oct 6, 2025Théophane Vallaeys, Jakob Verbeek, Matthieu CordImage Tokenization Image Reconstruction
Meta Fundamental AI Research · Sorbonne University
Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One
Date pendingFred Zhangzhi Peng, Kaiwen Zheng, Anru R. ZhangDiffusion Model Distillation One-Step Generative Modeling
Duke University · Tsinghua University

Apr 16, 2026, cs.CVJ/K move · Enter open · S save

TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation

Xiangyu Liu, Feng Gao, Xiaomei Zhang, Yong Zhang+3

1MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · 3Meituan+2

Audio-Video Generation Video Diffusion Models Diffusion Model Distillation Talking Head Generation Diffusion Distillation One-Step Generative Modeling

Open paper AskPDF arXiv

Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches can significantly accelerate inference, they often suffer from training instability. To address this challenge, we propose TurboTalk, a two-stage progressive distillation framework that effectively compresses a multi-step audio-driven video diffusion model into a single-step generator. We first adopt Distribution Matching Distillation to obtain a strong and stable 4-step student, and then progressively reduce the denoising steps from 4 to 1 through adversarial distillation. To ensure stable training under extreme step reduction, we introduce a progressive timestep sampling strategy and a self-compare adversarial objective that provides an intermediate adversarial reference that stabilizes progressive distillation. Our method achieve single-step generation of video talking avatar, boosting inference speed by 120 times while maintaining high generation quality.

Momentum

Related topics

Latest papers 97