TheSequence

Home
Archive
About
NewTopDiscussion
The new generative AI model shows significant efficiency improvements over models like Stable Diffusion, Imagen and Parti.
An overview of the AI techniques behind OpenAI's new supermodel
Sundays, The Sequence Scope brings a summary of the most important research papers, technology releases and VC funding deals in the artificial…
Sundays, The Sequence Scope brings a summary of the most important research papers, technology releases and VC funding deals in the artificial…
get those juicy bits, dirty hacks, and pragmatic workarounds from ML people in the trenches
+retrieval augmented diffusion models; +Stable Diffusion interfaces
+the original VQGAN+CLIP paper; +VQGAN+CLIP implementations
In this issue: we classify ML interpretability methods; we explore the building blocks of interpretability by Google Research; we explain TensorWatch…
Global model-agnostic interpretability, student-teacher intrepetability methods and the Lucid library.
Model-intrinsic vs. post-hoc interpretability, activation atlases visualizations and TensorBoard.
1
Sundays, The Sequence Scope brings a summary of the most important research papers, technology releases and VC funding deals in the artificial…
The new model combines GLIDE with image-to-3D generation models is a very clever and efficient architecture.
© 2023 Jesus Rodriguez, Ksenia Semenova
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing