1 citations · 1 across the 7 of their papers we have counts for
8 papers
Wasserstein Bounds for Ambient and Latent Smoothing on Data Manifolds
Wonjun Lee, Wenyan Luo
Smoothing empirical data can fill gaps between observations, while noise in the surrounding space can move mass away from the manifold supporting the data. We derive Wasserstein er…
Understanding Latent Diffusability via Fisher Geometry
Jing Gu, Morteza Mardani, Wonjun Lee +2
Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood. We quantify latent-space diffusability via the rate of change of the Minimum Mean S…
IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
Tien-Cuong Bui, Injae Chung, Wonjun Lee +2
Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig str…
Dynamics Over Landscape: The Emergence of Linear Separability via Spectral Alignment in Contrastive Learning
Jeff Calder, Wonjun Lee
Contrastive learning effectively clusters data despite a loss landscape filled with poor solutions, a success that is heavily dependent on the choice of data augmentations. How opt…
Geometry-Preserving Encoder/Decoder in Latent Generative Models
Wonjun Lee, Riley C. W. O'Neill, Dongmian Zou +2
Generative modeling aims to generate new data samples that resemble a given dataset. When using diffusion models for this task, one of the main challenges is solving the problem in…
Improving Hyperbolic Representations via Gromov-Wasserstein Regularization
Yifei Yang, Wonjun Lee, Dongmian Zou +1
Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly ap…
Monotone discretizations of levelset convex geometric PDEs
Jeff Calder, Wonjun Lee
We introduce a novel algorithm that converges to level-set convex viscosity solutions of high-dimensional Hamilton-Jacobi equations. The algorithm is applicable to a broad class of…
Monotone Generative Modeling via a Gromov-Monge Embedding
Wonjun Lee, Yifei Yang, Dongmian Zou +1
Generative adversarial networks (GANs) are popular for generative tasks; however, they often require careful architecture selection, extensive empirical tuning, and are prone to mo…