YoVDO

D-Flow: Differentiating through Flows for Controlled Generation

Offered By: Valence Labs via YouTube

Tags

Diffusion Models Courses Image Processing Courses Audio Processing Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a comprehensive conference talk on D-Flow, a framework for controlled generation in AI models. Delve into the intricacies of differentiating through flows to optimize generation outcomes in diffusion and flow-matching models without retraining. Discover how this approach unlocks powerful tools for inverse problems and conditional generation. Learn about the key observation that differentiating through the generation process projects gradient on the data manifold, implicitly incorporating prior knowledge. Examine the framework's validation on linear and non-linear controlled generation problems, including image and audio inverse problems and conditional molecule generation. Follow along as the speaker covers background information, controlled generation concepts, D-Flow methodology, theoretical intuitions, experimental results, and conclusions, concluding with an insightful Q&A session.

Syllabus

- Intro + Background
- Controlled Generation
- D-Flow
- Theoretical Intuition
- Experiments
- Conclusions
- Q+A


Taught by

Valence Labs

Related Courses

Introduction to Digital Sound Design
Emory University via Coursera
Foundations of Wavelets and Multirate Digital Signal Processing
Indian Institute of Technology Bombay via Swayam
iOS Development for Creative Entrepreneurs
University of California, Irvine via Coursera
Deploying TinyML
Harvard University via edX
Digital Signal Processing
École Polytechnique Fédérale de Lausanne via Coursera