3 papers
cs.LG2026
Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
Jinseong Park, Mijung Park
Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies primarily on loss maximization over f…
cs.LG2025
Revisiting Bayesian Model Averaging in the Era of Foundation Models
Mijung Park
We revisit the classical, full-fledged Bayesian model averaging (BMA) paradigm to ensemble pre-trained and/or lightly-finetuned foundation models to enhance the classification perf…
stat.ML2025
DP-LDMs: Differentially Private Latent Diffusion Models
Michael F. Liu, Saiyue Lyu, Margarita Vinaroz +1
Diffusion models (DMs) are one of the most widely used generative models for producing high quality images. However, a flurry of recent papers points out that DMs are least private…