Publications

Selected and recent publications. For a live citation index, see Google Scholar.

Recent conference papers

  1. The Safety-Aware Denoiser for Text Diffusion Models. Amman Yusuf, Zhejun Jiang, and Mijung Park. ICML 2026.
  2. Safety-Guided Flow (SGF): A Unified Framework For Negative Guidance In Safe Generation. Mingyu Kim, Young Heon Kim, and Mijung Park. ICLR 2026, oral presentation.
  3. Training-Free Safe Denoisers for Safe Use of Diffusion Models. Mingyu Kim, Dongjun Kim, Amman Yusuf, Stefano Ermon, and Mijung Park. NeurIPS 2025.
  4. Bayesian Principles Improve Prompt Learning In Vision-Language Models. Mingyu Kim, Jongwoo Ko, and Mijung Park. AISTATS 2025.
  5. Hermite Polynomial Features for Private Data Generation. Margarita Vinaroz, Mohammad-Amin Charusaie, Frederik Harder, Kamil Adamczewski, and Mijung Park. ICML 2022.
  6. DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-preserving Data Generation. Frederik Harder, Kamil Adamczewski, and Mijung Park. AISTATS 2021.
  7. Dirichlet Pruning for Convolutional Neural Networks. Kamil Adamczewski and Mijung Park. AISTATS 2021.
  8. Interpretable and Differentially Private Predictions. Frederik Harder, Matthias Bauer, and Mijung Park. AAAI 2020.
  9. Radial and Directional Posteriors for Bayesian Deep Learning. Changyong Oh, Kamil Adamczewski, and Mijung Park. AAAI 2020.
  10. DP-EM: Differentially Private Expectation Maximization. Mijung Park, James Foulds, Kamalika Chaudhuri, and Max Welling. AISTATS 2017.
  11. K2-ABC: Approximate Bayesian Computation with Kernel Embeddings. Mijung Park, Wittawat Jitkrittum, and Dino Sejdinovic. AISTATS 2016, oral presentation.

Journal papers

  1. Differentially Private Neural Tangent Kernels (DP-NTK) for Privacy-Preserving Data Generation. Yilin Yang, Kamil Adamczewski, Xiaoxiao Li, Danica J. Sutherland, and Mijung Park. JAIR 2025.
  2. Differentially Private Latent Diffusion Models. Michael F. Liu, Saiyue Lyu, Margarita Vinaroz, and Mijung Park. TMLR 2024.
  3. Differentially Private Kernel Inducing Points using Features from ScatterNets for Privacy Preserving Data Distillation. Margarita Vinaroz and Mijung Park. TMLR 2024.
  4. Pre-trained Perceptual Features Improve Differentially Private Image Generation. Frederik Harder, Milad Jalali, Danica J. Sutherland, and Mijung Park. TMLR 2023.
  5. Differentially Private Stochastic Expectation Propagation. Margarita Vinaroz and Mijung Park. TMLR 2022.
  6. ABCDP: Approximate Bayesian Computation with Differential Privacy. Mijung Park, Margarita Vinaroz, and Wittawat Jitkrittum. Entropy 2021.
  7. Variational Bayes In Private Settings (VIPS). Mijung Park, James Foulds, Kamalika Chaudhuri, and Max Welling. JAIR 2020.