Related papers: Boosting Alignment for Post-Unlearning Text-to-Ima…
Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…
Recent advances in image generation models (IGMs), particularly diffusion-based architectures such as Stable Diffusion (SD), have markedly enhanced the quality and diversity of AI-generated visual content. However, their generative…
We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful…
Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted…
Personalized text-to-image generation aims to create images tailored to user-defined concepts and textual descriptions. Balancing the fidelity of the learned concept with its ability for generation in various contexts presents a significant…
Recent regulation on right-to-be-forgotten emerges tons of interest in unlearning pre-trained machine learning models. While approximating a straightforward yet expensive approach of retrain-from-scratch, recent machine unlearning methods…
Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the increasing attention to this problem, it remains an open research question how to evaluate unlearning in…
Despite advancements in text-to-image generation (T2I), prior methods often face text-image misalignment problems such as relation confusion in generated images. Existing solutions involve cross-attention manipulation for better…
Robot learning methods have the potential for widespread generalization across tasks, environments, and objects. However, these methods require large diverse datasets that are expensive to collect in real-world robotics settings. For robot…
Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while potentially degrading model performance on both related and…
Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…
Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…
Machine unlearning aims to remove the influence of problematic training data after a model has been trained. The primary challenge in machine unlearning is ensuring that the process effectively removes specified data without compromising…
Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…
Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…
How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlearning', a novel paradigm that enables the targeted removal of…
Machine Unlearning aims to remove specific data from trained models, addressing growing privacy and ethical concerns. We provide a theoretical analysis of a simple and widely used method - gradient ascent - used to reverse the influence of…
Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…
We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…