Country
DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification Kaibo Wang
Diffusion-based purification has demonstrated impressive robustness as an adversarial defense.
Class-Conditional Conformal Prediction with Many Classes
We propose a method called clustered conformal prediction that clusters together classes having "similar" conformal
Lo-Hi: Practical ML Drug Discovery Benchmark
Finding new drugs is getting harder and harder. One of the hopes of drug discovery is to use machine learning models to predict molecular properties.
CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM
Single particle cryo-electron microscopy (cryo-EM) is a widely used imaging technique for visualizing biomolecular complexes at near-atomic resolution.
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
We further show the mismatched sampling paradox: A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior.
LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation Jiajun Tang
Advanced image editing is in high demand across a multitude of applications, e.g ., old photo