Efficient Generative Models for Visual Synthesis
Name
yin-tianweiy-phd-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
19.42 MB
Format
Adobe PDF
Checksum (MD5)
05569ff8a9d5df8c82ac02da555c365a
Author(s)
Yin, Tianwei
Advisor(s)
Freeman, William T.
Durand, Frédo
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
While current visual generative models produce high-quality outputs, they suffer from significant computational costs and latency, limiting their applicability in interactive settings. In this dissertation, we introduce a suite of techniques designed to enhance the efficiency of generative models for image and video synthesis. First, we propose distribution matching distillation, a method that enables the training of one- or few-step visual generators by distilling knowledge from computationally expensive yet highly capable diffusion models. Next, we develop improved distillation techniques that enhance robustness and scalability, culminating in a production-grade few-step image generator. This system is now deployed in widely used software, generating hundreds of millions of images annually. Finally, we extend our approach to video generation by adopting an autoregressive paradigm, significantly reducing latency and enabling fast interactive video generation and world simulation.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
