Log inSign up
Kwangjun Ahn
73 posts
@KwangjunA

Kwangjun Ahn

@KwangjunA
Researcher at NVIDIA // ex-Researcher at Microsoft, PhD from MIT EECS
Cambridge, MA
kjahn.mit.edu
Joined February 2020
317
Following
735
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @KwangjunA
    Kwangjun Ahn
    @KwangjunA
    Sep 29, 2025
    New improvement in Dion leads to a speedup that makes orthonormal updates (eg. Muon) more scalable for larger matrices. The trick: carefully using Newton-Schulz (on smaller matrices) as Dion's backend. Updates to our microsoft/dion codebase are coming soon---stay tuned!
    Image
    1
  • @KwangjunA
    Kwangjun Ahn
    @KwangjunA
    Jul 15, 2025
    ICML: come check out our Oral Presentation on Schedule-free training theory based on an elegant online learning!
    Image
  • @KwangjunA
    Kwangjun Ahn
    @KwangjunA
    Apr 23, 2025
    ICLR: @edward_s_hu and I will be presenting our work "The Belief State Transformer" at the 1st poster session. (#269) Please come check it out! (github: github.com/microsoft/BST)
    Image
    GitHub - microsoft/BST
    From github.com
  • @KwangjunA
    Kwangjun Ahn
    @KwangjunA
    Jul 23, 2024
    Come to my presentation of ICML 2024 paper tmrw at 1:30–3 pm! We provide a new perspective on Adam optimizer based on online learning. In particular, our perspective shows the importance of Adam's key components. (video: youtu.be/AU39SNkkIsA)
    Image
  • @KwangjunA
    Kwangjun Ahn
    @KwangjunA
    Jun 25, 2024
    In our ICML 2024 paper (@icmlconf), joint w/ Zhiyu Zhang (@imZhiyuZ), Yunbum Kook, Yan Dai, we provide a new perspective on Adam optimizer based on online learning. In particular, our perspective shows the importance of Adam's key components. (video: youtu.be/AU39SNkkIsA)
    Image
Advertisement
Advertisement