Related papers: LURE: Latent Space Unblocking for Multi-Concept Re…

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…

Text-to-image diffusion models have an unprecedented ability to generate diverse and high-quality images. However, they often struggle to faithfully capture the intended semantics of complex input prompts that include multiple subjects.…

Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation…

The rapid progress of visual autoregressive (VAR) models has brought new opportunities for text-to-image generation, but also heightened safety concerns. Existing concept erasure techniques, primarily designed for diffusion models, fail to…

Most existing Low-light Image Enhancement (LLIE) methods either directly map Low-Light (LL) to Normal-Light (NL) images or use semantic or illumination maps as guides. However, the ill-posed nature of LLIE and the difficulty of semantic…

LEARN is a layout-aware diffusion framework designed to generate pedagogically aligned illustrations for STEM education. It leverages a curated BookCover dataset that provides narrative layouts and structured visual cues, enabling the model…

The widespread adoption of diffusion models in image generation has increased the demand for privacy-compliant unlearning. However, due to the high-dimensional nature and complex feature representations of diffusion models, achieving…

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…

Recent advances in large-scale diffusion models have intensified concerns about their potential misuse, particularly in generating realistic yet harmful or socially disruptive content. This challenge has spurred growing interest in…

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…

Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector control found in GANs,…

Despite significant advances in quality and complexity of the generations in text-to-image models, prompting does not always lead to the desired outputs. Controlling model behaviour by directly steering intermediate model activations has…

The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…

The completion, extension, and generation of 3D semantic scenes are an interrelated set of capabilities that are useful for robotic navigation and exploration. Existing approaches seek to decouple these problems and solve them one-off.…

Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets,…

Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis. Prior works mostly rely on pre-trained linguistic models, but a text is often too abstract to properly specify all the…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To…

Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…