A method that can recover the weights of the pre-fine-tuning model using a few low-rank (LoRA) fine-tuned models. In contrast to previous attacks that attempt to recover pre-fine-tuning capabilities, Spectral DeTuning aims to recover the exact pre-fine-tuning *weights*. Spectral DeTuning can exploit this vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.

Method that adapts expectation-maximization (EM) to aggregate annotations that work on tasks with combined localization and classification like object detection and instance segmentation.

LAEM

Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels

Spectral DeTuning

Recovering the Pre-Fine-Tuning Weights of Generative Models

MixLoRA is a type of PEFT method which construct a resource-efficient sparse MoE model based on LoRA.

Source	Recovering the Pre-Fine-Tuning Weights of Generative Models
Year
Data Source	Papers with Code archive (CC BY-SA)