3 citations · 7 across the 10 of their papers we have counts for
10 papers
EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
Abhiram Kusumba, Maitreya Patel, Kyle Min +3
Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image qua…
A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models
Changhoon Kim, Yanjun Qi
Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyr…
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
Maitreya Patel, Abhiram Kusumba, Sheng Cheng +4
Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the train…
Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation
Utkarsh Nath, Rajeev Goel, Eun Som Jeon +5
To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generati…
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
Changhoon Kim, Kyle Min, Yezhou Yang
In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability to generate high-quality images from textual descriptions faces challenges with the pot…
Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
Jinyung Hong, Eun Som Jeon, Changhoon Kim +5
Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit th…
ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations
Maitreya Patel, Changhoon Kim, Sheng Cheng +2
Text-to-image (T2I) diffusion models, notably the unCLIP models (e.g., DALL-E-2), achieve state-of-the-art (SOTA) performance on various compositional T2I benchmarks, at the cost o…
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
Changhoon Kim, Kyle Min, Maitreya Patel +2
The rapid advancement of generative models, facilitating the creation of hyper-realistic images from textual descriptions, has concurrently escalated critical societal concerns suc…
Attributing Image Generative Models using Latent Fingerprints
Guangyu Nie, Changhoon Kim, Yezhou Yang +1
Generative models have enabled the creation of contents that are indistinguishable from those taken from nature. Open-source development of such models raised concerns about the ri…
Attributable-Watermarking of Speech Generative Models
Yongbaek Cho, Changhoon Kim, Yezhou Yang +1
Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as mal…