Wednesday, July 16, 2025
LBNN
  • Business
  • Markets
  • Politics
  • Crypto
  • Finance
  • Energy
  • Technology
  • Taxes
  • Creator Economy
  • Wealth Management
  • Documentaries
No Result
View All Result
LBNN

Expanding the use and scope of AI diffusion models

Simon Osuji by Simon Osuji
April 3, 2025
in Artificial Intelligence
0
Expanding the use and scope of AI diffusion models
0
SHARES
0
VIEWS
Share on FacebookShare on Twitter


Expanding the use and scope of AI diffusion models
UC San Diego’s Geisel Library arising from the denoising process. Credit: Yian Ma, HDSI

Researchers at the University of California San Diego and other institutions are working on a way to make a type of artificial intelligence (AI) called diffusion models—a type of AI that can generate new content such as images and videos by training on large datasets—more efficient and widely applicable.

Related posts

DHS Faces New Pressure Over DNA Taken From Immigrant Children

DHS Faces New Pressure Over DNA Taken From Immigrant Children

July 16, 2025
New research reveals AI has a confidence problem

New research reveals AI has a confidence problem

July 16, 2025

Currently, diffusion models work by making small, incremental changes to input data, allowing the model to learn complex patterns and relationships—a process that can be slow and limited in application. So Yian Ma, an assistant professor at UC San Diego’s Halıcıoğlu Data Science Institute (HDSI), part of the School of Computing, Information and Data Sciences, and his research colleagues have developed a new approach that allows for larger jumps in between steps, making the process faster and more flexible.

In a recent paper titled “Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference,” Ma and researchers at the University of Illinois Urbana-Champaign (UIUC), the Hong Kong University of Science and Technology (HKUST), the University of Hong Kong (HKU) and Salesforce AI Research presented an analysis of a generalized version of diffusion models.

The paper was recognized as a spotlight paper at NeurIPS 2024—one of the largest conferences in machine learning—and it was awarded best paper at the International Conference on Machine Learning (ICML 2024) workshop: “Structured probabilistic inference and generative modeling.”

“Classical diffusion models incrementally add small, Gaussian noise (a normal random variable with a small amplitude) to transform the data distribution toward a simple, standard normal distribution. The models then learn functions to specify the incremental changes and ‘denoise’ to transform the standard normal random variable back to one that follows the data distribution,” Ma said.

According to Ma, however, the research team does not require the incremental updates to be small Gaussian noise. Instead, they consider larger jumps in between steps that follow distributions beyond the normal ones. These can be long-tailed distributions or even distributions generated by subroutine algorithms. Using this technique, the researchers were able to reduce the number of intermediary steps and accelerate the algorithm for the diffusion models, making them more widely applicable to various tasks.

“We can see that such generalization improves the efficiency of the diffusion models. Potentially, it could also lead to much wider usage of diffusion models, such as language generation and more interestingly, long-term reasoning and decision making,” Ma said.

In addition to Ma, the research team includes Xupeng Huang, currently a visiting student at HDSI; Tong Zhang, from UIUC; Difan Zou and Yi Zhang from HKU; and Hanze Dong from Salesforce.

“What’s most exciting about this work is that it can make use of almost any intermediary transition step, that can both accelerate the algorithm and make the algorithm more widely applicable to various downstream tasks,” Ma said. “I would expect this work to be applied to text generation and multi-modal generation, long-term reasoning, tool using and problem solving, as well as decision-making tasks to both accelerate and improve the outcomes of such tasks.”

More information:
Paper: Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference

Provided by
University of California – San Diego

Citation:
Expanding the use and scope of AI diffusion models (2025, April 3)
retrieved 3 April 2025
from https://techxplore.com/news/2025-04-scope-ai-diffusion.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Previous Post

Electricity: TotalEnergies acquires renewable portfolios in Europe, Africa, Canada – EnviroNews

Next Post

Dow Drops 1,400 Points as Markets Nosedive on Trump Tariffs

Next Post
Dow Drops 1,400 Points as Markets Nosedive on Trump Tariffs

Dow Drops 1,400 Points as Markets Nosedive on Trump Tariffs

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

RECOMMENDED NEWS

How Boston sports fans (unknowingly?) saved one of hardcore’s most influential labels

How Boston sports fans (unknowingly?) saved one of hardcore’s most influential labels

2 years ago
A Cookbook For The Community!

A Cookbook For The Community!

7 months ago
Ins and Outs of Domestic Asset Protection Trusts (DAPTs)

Ins and Outs of Domestic Asset Protection Trusts (DAPTs)

1 year ago
California State Representative to Draft Pro-Bitcoin Legislation

California State Representative to Draft Pro-Bitcoin Legislation

6 months ago

POPULAR NEWS

  • Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    0 shares
    Share 0 Tweet 0
  • When Will SHIB Reach $1? Here’s What ChatGPT Says

    0 shares
    Share 0 Tweet 0
  • The world’s top 10 most valuable car brands in 2025

    0 shares
    Share 0 Tweet 0
  • Tanzania’s natural gas sector goes global with Dubai deal

    0 shares
    Share 0 Tweet 0
  • Top 10 African countries with the highest GDP per capita in 2025

    0 shares
    Share 0 Tweet 0
  • Privacy Policy
  • Contact

© 2023 LBNN - All rights reserved.

No Result
View All Result
  • Home
  • Business
  • Politics
  • Markets
  • Crypto
  • Economics
    • Manufacturing
    • Real Estate
    • Infrastructure
  • Finance
  • Energy
  • Creator Economy
  • Wealth Management
  • Taxes
  • Telecoms
  • Military & Defense
  • Careers
  • Technology
  • Artificial Intelligence
  • Investigative journalism
  • Art & Culture
  • Documentaries
  • Quizzes
    • Enneagram quiz
  • Newsletters
    • LBNN Newsletter
    • Divergent Capitalist

© 2023 LBNN - All rights reserved.