Log inSign up
Log inSign up
Yilun Kuang
133 posts
@KuangYilun

Yilun Kuang

@KuangYilun
PhD Student @NYUDataScience & @CILVRatNYU
NYC
yilunkuang.github.io
Joined March 2019
518 Following
535 Followers
RepliesRepliesRepostsRepostsMediaMedia

Yilun Kuang’s posts

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·US TIDA·Ads Info·© 2026 X Corp.
  • Pinned
    @KuangYilun
    Yilun Kuang
    @KuangYilun
    Aug 26
    Introducing LpWM: A Case for Sparse Representations in World Models Dense Gaussian representations are a choice, not a requirement. We find that sparse representations can make latent dynamics easier to model for planning. 📄arxiv.org/abs/2608.22764 💻github.com/YilunKuang/lpw…
    Lucas Maes and 4 others
    15
  • @KuangYilun
    Yilun Kuang
    @KuangYilun
    Nov 19
    Slow SVReg learns the geometry of the underlying world. Another step towards better regularization for JEPAs!
    @mengyer
    Mengye Ren
    @mengyer
    Nov 19
    Can a JEPA learn a latent map of the world? We released a new paper with @yingwww_ @choang333 @KuangYilun @ylecun 🧵
    00:00
  • @KuangYilun
    Yilun Kuang
    @KuangYilun
    Mar 18
    Check out this writeup about our Rectified LpJEPA paper from the NYU CDS team!
    @NYUDataScience
    NYU Center for Data Science
    @NYUDataScience
    Mar 18
    CDS PhD student @KuangYilun, CDS founding director @ylecun, former CDS Faculty Fellow @timrudner, and others successfully applied biological sparsity to AI. Their new technique allows computer vision models to ignore 90% of data without losing accuracy. nyudatascience.medium.com/new-representa…
  • @KuangYilun
    Yilun Kuang
    @KuangYilun
    Feb 18
    Very cool work in identifying why diffusion struggles in representation space! From the representation learning side, we have also developed a technique in our Radial-VCReg paper (arxiv.org/abs/2602.14272) to prevent radial entropy collapse by regularizing the entropy of the
    @Amandeep__kumar
    Amandeep Kumar
    @Amandeep__kumar
    Feb 11
    🚀 Unlocking Standard Diffusion Transformers on Representation Encoders Why do standard DiTs fail to converge on high-dimensional features like DINOv2? 📉 We found the answer isn't just "more parameters"—it's Geometry. Introducing Riemannian Flow Matching with Jacobi
    2
  • @KuangYilun
    Yilun Kuang
    @KuangYilun
    Feb 3
    How do we build sparsity into JEPA representations by design, while preserving task-relevant information? Introducing Rectified LpJEPA, a JEPA architecture that learns sparse, non-negative, informative representations through principled distributional regularization. 📐 📄 Paper: arxiv.org/abs/2602.01456 💻 Code: github.com/YilunKuang/rec… 📝 Blog: yilunkuang.github.io/blog/2026/rect… (1/n)
    Yash Dagade and 2 others
    31