Improving generative modelling with Shortest Path Diffusion (ICML paper)

Jun 24, 2023
AI
Improving generative modelling with Shortest Path Diffusion (ICML paper)

Diffusion models are currently the most popular algorithms for data generation, with applications in image synthesis, video generation, and molecule design. MediaTek Research has just published a paper showing that the performance of diffusion models is boosted by optimizing the diffusion process to minimize the path taken from the initial to the final data distribution. This contribution will improve the efficiency and quality of diffusion models, especially by reducing the resources necessary for generation and synthesis. The AI research group will present this work at the ICML conference in July.

Related Articles

MediaTek at MWC 2024 - Generative AI

Feb 28, 2024

MediaTek at MWC 2024 - 1st with LoRA Fusion on smartphones

Feb 26, 2024

MediaTek Dimensity 9300 and 8300 Chipsets Now Optimized for Google Gemini Nano

Feb 22, 2024
MTK Highlights

Sign up for our monthly newsletter

EXECUTIVE INSIGHTS | LATEST NEWS & EVENTS | PRODUCTS & TECHNOLOGIES