Feature-wise transformations

A simple and surprisingly effective family of conditioning mechanisms.

Feature-wise transformations Distill Feature-wise transformations A simple and surprisingly effective family of conditioning mechanisms. Authors Affiliations Vincent Dumoulin Google Brain Ethan Perez Rice University , MILA Nathan Schucher Element AI Florian Strub Univ. of Lille, Inria Harm de Vries MILA Aaron Courville MILA Yoshua Bengio MILA Published July 9, 2018 DOI 10.23915/distill.00011 Many real-world problems require integrating multiple sources of information. Sometimes these problems involve multiple, distinct modalities of information — vision, language, audio, etc. — as is required

saved by

• Winnie Xu
• Noah T
• Davis Brown

related reading

• Feature Visualizationdistill.pub
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• Transformers from Scratche2eml.school
• Transformer Explainer: LLM Transformer Model Visually Explainedpoloclub.github.io
• Feature Visualizationdistill.pub
• The Annotated Transformernlp.seas.harvard.edu
• Painting With Concepts Using Diffusion Model Latentsgoodfire.ai
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub