Juho Lee

19

Papers

72

Total Citations

Papers (19)

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

Dimension Agnostic Neural Processes

Variational Bayesian Pseudo-Coreset

Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts

Learning to Explore for Stochastic Gradient MCMC

A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data

A Multi-Mode Modulator for Multi-Domain Few-Shot Classification

Bootstrapping neural processes

NeurIPS 2020arXiv

Neural Complexity Measures

NeurIPS 2020arXiv

Diversity Matters When Learning From Ensembles

NeurIPS 2021arXiv

Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding

NeurIPS 2021arXiv

On Divergence Measures for Bayesian Pseudocoresets

NeurIPS 2022arXiv

Set-based Meta-Interpolation for Few-Task Meta-Learning

NeurIPS 2022arXiv

Function Space Bayesian Pseudocoreset for Bayesian Neural Networks

NeurIPS 2023arXiv