Here are Papers I Reviewed. I am science curious.

  • This website aims to educate myself (+my collaborators) to catch up with the fast growing AI literature and Deep learning Tech.
  • This website includes a (growing) list of tech materials I read for the above purpose.
  • I hope this website helps people who share similar interests or want to learn similar topics.
  • Please feel free to email me (yanjun.research@gmail.com), if you have comments, questions or recommendations.

– By [Dr. Yanjun Qi] @https://qiyanjun.github.io/Homepage/

About the Sidebar and how we group the readings

  • Due to the large number of readings, I try to organize them according to three different variables. Each variable maps to one item in this website’s top header bar.

  • ByCategory: for our readings since 2022 on Generative AI, we group our readings to 4 general groups: FM Basics , FM Adapt , FM Risk , FM Multi)

  • ByCategory: for our readings from 2017 to 2020 on deep learning, we group our readings to 10 general groups: 0Basics , 1Theoretical , 2Architecture , 2Graphs , 3Reliable , 4Optimization , 5Generative , 6Reinforcement , 7MetaDomain , 8Scalable , 9DiscreteApp.

  • You can also check out these categories as a whole and their relevant readings via Readings ByCategory . As shortcuts, we also add each category’s page URL as a single item (sorted by Category Names) in our side bar.

  • ByTags: we use 150 different tags to organize deep learning papers we reviewed. Please check out these tags via Readings ByTag .

  • ByReadDates: our review slides were done in multiple different semesters (2017Fall, 2018Club, 2019Spring, 2019Fall). To help my students (from a specific semester) navigate, I also group our reading sessions according to what semester a review session has happened at (via my seminar courses or via my journal club). Please check out our readings sorted by semesters via Readings ByReadDate

Claim

  • The covered readings are by no means an exhaustive list, but are topics that I learned or plan to learn.