JapanTech

Diffusion Models: From Foundations to a Working Application

Tokyo AI technical session on diffusion models: flow matching foundations, diffusion language models and discrete-domain uses.

When
Wed, November 18, 2026 · 18:00–21:00 JST
Where
Tokyo, Japan · In person
Region
Kanto (Tokyo)
Organizer
Tokyo AI
Language
EN
Source
Luma
Summary
Tokyo AI (TAI) hosts a technical session on diffusion models, moving from the foundations of diffusion and flow matching to diffusion language models and applications in text and other discrete domains. The format is three complementary talks with Q&A, followed by discussion and networking. The confirmed talk, "Understanding Diffusion and Flow Matching", is by Xuan Zhang, a machine learning engineer at SmartNews, and focuses on intuition and demos rather than derivations. November 18 is the preferred date with November 20 as a fallback; the venue in Tokyo, the other speakers and the timings are still provisional. Aimed at ML practitioners, AI engineers, researchers and research students.
About the community

Tokyo AI is a large international AI community based in Tokyo, bringing together engineers, researchers, investors and product people. It runs frequent English-language technical talks, panels and networking evenings connecting Japan's AI builders with the global ecosystem.

#diffusion-models#flow-matching#generative-ai#llm#machine-learning#diffusion-llm#tech-talk#tokyo