Ablating concepts in text-to-image diffusion models

N Kumari, B Zhang, SY Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Large-scale text-to-image diffusion models can generate high-fidelity images with powerful
compositional ability. However, these models are typically trained on an enormous amount …

Editing large language models: Problems, methods, and opportunities

Y Yao, P Wang, B Tian, S Cheng, Z Li, S Deng… - arXiv preprint arXiv …, 2023 - arxiv.org
Despite the ability to train capable LLMs, the methodology for maintaining their relevancy
and rectifying errors remains elusive. To this end, the past few years have witnessed a surge …

Forget-me-not: Learning to forget in text-to-image diffusion models

G Zhang, K Wang, X Xu, Z Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
The significant advances in applications of text-to-image generation models have prompted
the demand of a post-hoc adaptation algorithms that can efficiently remove unwanted …

Rethinking machine unlearning for large language models

S Liu, Y Yao, J Jia, S Casper, N Baracaldo… - arXiv preprint arXiv …, 2024 - arxiv.org
We explore machine unlearning (MU) in the domain of large language models (LLMs),
referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence …

Unified concept editing in diffusion models

R Gandikota, H Orgad, Y Belinkov… - Proceedings of the …, 2024 - openaccess.thecvf.com
Text-to-image models suffer from various safety issues that may limit their suitability for
deployment. Previous methods have separately addressed individual issues of bias …

[HTML][HTML] Combined scaling for zero-shot transfer learning

H Pham, Z Dai, G Ghiasi, K Kawaguchi, H Liu, AW Yu… - Neurocomputing, 2023 - Elsevier
Recent developments in multimodal training methodologies, including CLIP and ALIGN,
obviate the necessity for individual data labeling. These approaches utilize pairs of data and …

Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation

C Fan, J Liu, Y Zhang, E Wong, D Wei, S Liu - arXiv preprint arXiv …, 2023 - arxiv.org
With evolving data regulations, machine unlearning (MU) has become an important tool for
fostering trust and safety in today's AI models. However, existing MU methods focusing on …

Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing

F Yang, S Yang, MA Butt… - Advances in Neural …, 2023 - proceedings.neurips.cc
Large-scale text-to-image generative models have been a ground-breaking development in
generative AI, with diffusion models showing their astounding ability to synthesize …

Selective amnesia: A continual learning approach to forgetting in deep generative models

A Heng, H Soh - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
The recent proliferation of large-scale text-to-image models has led to growing concerns that
such models may be misused to generate harmful, misleading, and inappropriate content …

Model sparsity can simplify machine unlearning

J Liu, P Ram, Y Yao, G Liu, Y Liu… - Advances in Neural …, 2024 - proceedings.neurips.cc
In response to recent data regulation requirements, machine unlearning (MU) has emerged
as a critical process to remove the influence of specific examples from a given model …