Cover Image for Diffusion Model Meetup & Paper Reading — Diffusion Model in Robotics + Literature Review and Common Architecture Grouping
Cover Image for Diffusion Model Meetup & Paper Reading — Diffusion Model in Robotics + Literature Review and Common Architecture Grouping
Avatar for AI Scholars
Presented by
AI Scholars
19 Went

Diffusion Model Meetup & Paper Reading — Diffusion Model in Robotics + Literature Review and Common Architecture Grouping

Zoom
Registration
Past Event
Welcome! To join the event, please register below.
About Event

TL;DR

In this session, we’ll explore how diffusion model can be applied in robotics, then break down how common different diffusion models connect — through perspectives like discrete vs. continuous time, forward vs. reverse processes, and unifying frameworks like Flow Matching and Stochastic Interpolants.

This is one of our first sessions for our new online Diffusion Model Paper Reading Group, open to everyone. We’re a small community of engineers and PM friends working in the AI field — based in NY, SF, Toronto, and Boston.

Requirements:

You’ll be fine as long as you have:

  • A basic understanding of how diffusion models work

  • Some Python (and ideally PyTorch) experience


🗓 What to Expect

First 30min: We will explore how diffusion model can be applied in robotics

Second 30min: We’ll break down common diffusion models by:

  • ⏱ Discrete-time vs Continuous-time

  • 🔁 Time-Reversals vs Solving the Fokker-Planck equation

  • 🔊 "Forward process" vs probability paths

  • 🧮 Flow Matching vs Stochastic Interpolants


📚 Pre-Class Learning
📘 Reference: Lecture Note 4.3 – A Guide to the Diffusion Model Literature

https://diffusion.csail.mit.edu/docs/lecture-notes.pdf

🧾 Paper: On the Design Fundamentals of Diffusion Models: A Survey

https://arxiv.org/pdf/2306.04542


👥 Who Is This For?

  • Engineers & PMs curious about GenAI

  • Early-stage researchers and technical artists

  • Builders who want to code, not just consume theory

  • Beginners welcome — no ML background required!


🧠 About the Diffusion Model Bootcamp

This session is part of our 5-month, peer-led learning journey — designed for curious engineers, PMs, researchers, and technical artists.

🔹 No ML background needed — just interest and 2–4 hours/week

🔹 Learn key architectures in the diffusion model landscape

🔹 Build your own GenAI app, train a model, and explore ComfyUI

🔹 Monthly paper readings, final project, and supportive peer group

📅 Next cohort begins, at a time to be determined

📣 Spots are limited — join this session to explore if it’s a fit!

👉 Questions? DM the organizer!

Avatar for AI Scholars
Presented by
AI Scholars
19 Went