Related papers: UnGuide: Learning to Forget with LoRA-Guided Diffu…

As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing methods overly prioritize efficiency and aggressive forgetting,…

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen…

The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure…

Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…

This paper describes LIBU (LoRA enhanced influence-based unlearning), an algorithm to solve the task of unlearning - removing specific knowledge from a large language model without retraining from scratch and compromising its overall…

Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing…

Diffusion models excel in generating high-quality images. However, current diffusion models struggle to produce reliable images without guidance methods, such as classifier-free guidance (CFG). Are guidance methods truly necessary?…

Generative models have been very popular in the recent years for their image generation capabilities. GAN-based models are highly regarded for their disentangled latent space, which is a key feature contributing to their success in…

We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is…

In the current digital era, facial recognition systems offer significant utility and have been widely integrated into modern technological infrastructures; however, their widespread use has also raised serious privacy concerns, prompting…

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase…

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…

Low-Rank Adaptation (LoRA) offers an efficient paradigm for customizing diffusion models, but its ease of redistribution raises concerns over unauthorized use and the generation of untraceable content. Existing watermarking techniques…

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques…

Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have…

Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain…

Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly…

As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy and governance requirements. This motivates selective unlearning, which suppresses…

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Classifier guidance -- using the gradients of an image classifier to steer the generations of a diffusion model -- has the potential to dramatically expand the creative control over image generation and editing. However, currently…