vault backup: 2024-10-30 15:17:08

201 Metadata/My Library.bib

@@ -11227,6 +11227,15 @@ Subject\_term: Careers, Politics, Policy},
   isbn = {1-4612-0577-8}
 }
 
+@online{SoraCreatingVideo,
+  title = {Sora: {{Creating}} Video from Text},
+  shorttitle = {Sora},
+  url = {https://openai.com/index/sora/},
+  urldate = {2024-10-30},
+  langid = {american},
+  file = {/home/danesabo/Zotero/storage/YUQHRZUS/sora.html}
+}
+
 @misc{sorensenLecturesCurryHowardIsomorphism,
   title = {Lectures on the {{Curry-Howard Isomorphism}}},
   author = {Sorensen, Morten Heine B. and Urzyczyn, Pawel},

4 Qualifying Exam/2 Writing/3. QE Research Approach.md

@@ -43,4 +43,4 @@ Something to justify, why diffusion model as opposed to other generative AI
 
 ## Writin some stuff
 
-The purpose of this proposal is to suggest that using a generative network to create unstructured perturbations can be a viable way to advance the state of the art. But to do this, the current state of diffusion models and their place must be introduced. The generative diffusion model is a recent breakthrough in generative models. Diffusion models 
+The purpose of this proposal is to suggest that using a generative network to create unstructured perturbations can be a viable way to advance the state of the art. But to do this, the current state of diffusion models and their place must be introduced. The generative diffusion model is a recent breakthrough in generative models [@sohl-dicksteinDeepUnsupervisedLearning2015]. Diffusion generative models are the state of the art for image and video generation, and have demonstrated promise for audio generation and noise removal  [@kongDiffWaveVersatileDiffusion2020] [@SoraCreatingVideo].  Diffusion models do this through a forward noise-inducing process, and a backwards