DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

Divergence Decoding (DD) is a novel, effective, and inexpensive method that uses auxiliary models to steer LLM logits during inference, enabling the removal of memorized sensitive data without signifi…

CoreUnlearn introduces a novel framework that disentangles and removes undesirable concepts from text-guided diffusion models by targeting specific, erasure-critical components of the concept embeddin…

This paper provides the first integrated analysis of model dememorization, unifying unlearnability and unlearning methods, and offering theoretical guarantees on dememorization depth.

The paper proposes a novel, theoretically-grounded algorithm (HAMU) that addresses the challenge of machine unlearning by guaranteeing specified improvements in forget quality while minimizing retain…

The paper introduces Asymmetric Langevin Unlearning (ALU), a novel framework that uses public data to significantly reduce the utility loss typically associated with certified machine unlearning, enab…

PURGE is a novel machine unlearning algorithm that leverages the duality between continual learning and unlearning to achieve high data retention while making the unlearned model indistinguishable fro…

The paper establishes tight upper and lower bounds on the statistical cost of approximate machine unlearning for smooth strongly convex losses, showing that the optimal unlearning rate depends critica…

This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper proposes DiReCT, a novel framework that treats data selection during LLM annealing as a constrained optimization problem based on the spectral geometry of the loss landscape, achieving state…

The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving…

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong gene…

This paper systematically investigates unlearnable examples (UEs) across diverse training paradigms, finding that existing UEs fail under pretraining-finetuning (PF) settings, and proposes Shallow Sem…

The paper introduces DSL-LLaDA, a method that lightly adapts a pre-trained masked diffusion language model to perform continuous denoising in embedding space, significantly improving text generation q…

This paper diagnoses a bias-dominated shortcut in class-level machine unlearning, where forgetting is achieved by suppressing classification head biases, and proposes bias-aware mechanisms to mitigate…

The paper proposes a semi-relaxed Gromov-Wasserstein objective to estimate the latent connectivity structure of large-scale networks, achieving statistically consistent and efficient recovery of the u…

The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…