NexT


  • Home

  • Archives

  • Tags

Three Road Diffusion

Posted on 2025-03-23 | In GenAI

Main Reference

Read more »

Diffusion Theory for Gaussian Mixture Model

Posted on 2025-03-23 | In GenAI

Main Reference

Read more »

Three Road Diffusion

Posted on 2025-03-23 | In GenAI

Excellent lectures!!!!: https://www.youtube.com/watch?v=8mxCNMJ7dHM&list=PL0H3pMD88m8XPBlWoWGyal45MtnwKLSkQ

Read more »

Stanford AI- Diffusion Lecture

Posted on 2025-03-18 | In GenAI

Excellent lectures!!!!: https://www.youtube.com/watch?v=8mxCNMJ7dHM&list=PL0H3pMD88m8XPBlWoWGyal45MtnwKLSkQ

Read more »

Generation via Flow Model

Posted on 2025-03-06 | In GenAI

[[2021-09-19-Deterministic_Probabilistic]]

Introduction

Read more »

Gaussian Invariant

Posted on 2025-03-02 | In GenAI

[[2021-09-19-Deterministic_Probabilistic]]

Introduction

Read more »

DeepSeek R1 On Naive Bayes and Logistic Regression

Posted on 2025-02-16 | In GenAI

Introduction

Read more »

Math AI - Score Matching is All U Need for Diffusion

Posted on 2025-02-02 | In GenAI

Yang Song 的 interview: “History of Diffusion” 提到

  • 爲什麽 focus on score matching 的關鍵是: MCMC sampling of $p_{data}(\mathbf{x})$ 太慢了。因爲只有 accept and reject. Score matching 因爲有指引所以快的多。
  • 很多人都說 score function 有非常多挑戰不可行。他也承認,但是初生之犢不怕虎。最後加上 gaussian noise 什麽問題都解決了!
  • Score matching 雖然快,缺點是比較注重在 local structure. MCMC 因爲有 partition function, 比較有全局觀。
  • 發展 SDE (continuous method) 是被 DDPM 刺激,可以結合 score matching and DDPM.
  • A remarkable result from Anderson (1982) states that the reverse of a diffusion process is also a diffusion process, running backwards in time and given by the reverse-time SDE:
  • Yang 也 surprise reverse SDE 的 close form (Anderson) 而且包含 score function!
  • 很自然從 ODE based on Fokker-Planck, 原來是爲了計算 likelihood, 沒想到可以加速。
  • 進一步 neural ODE 得到 consistency model, 2 step 就可以得到 comparable quality image. 同時可以解釋 flow model. 一般 flow model 使用 reciprocal function, 但是也可以用 ODE 于 reciprocal function!
  • UNET 是最適合 score function.
  • No surprise of stable diffusion (Unet on latent). DiT 才是真正 transformer based.
  • Consistency model 是另一個 AR, Diffusion 之外的 generative method. 很看好
Read more »

Math Stat I - Likelihood, Score Function, and Fisher Information

Posted on 2025-02-01 | In GenAI
Read more »

Generative AI- Diffusion Lecture

Posted on 2025-01-18 | In Science

Main Reference

Read more »
1 … 4 5 6 … 35
Allen Lu (from John Doe)

Allen Lu (from John Doe)

341 posts
8 categories
230 tags
RSS
© 2026 Allen Lu (from John Doe)
Powered by Jekyll
Theme - NexT.Muse