相关论文: ConceptSplit: Decoupled Multi-Concept Personalizat…

Multimodal foundation models are increasingly trained on sensitive data across domains such as finance, biomedicine, and personal identifiers. However, this distributed setup raises serious privacy concerns due to the need for…

Numerous studies on text-to-image (T2I) generative models have utilized cross-attention maps to boost application performance and interpret model behavior. However, the distinct characteristics of attention maps from different attention…

Diffusion models have become a powerful backbone for text-to-image generation, producing high-quality visuals from natural language prompts. However, when prompts involve multiple objects alongside global or local style instructions, the…

Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily…

The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or sensitive imagery. As a practical solution, machine unlearning aims to erase unwanted…

Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with…

Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by…

Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer…

This paper addresses the challenge of data scarcity in semantic segmentation by generating datasets through text-to-image (T2I) generation models, reducing image acquisition and labeling costs. Segmentation dataset generation faces two key…

Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that…

Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capabilities, they face critical limitations in image editing…

Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…

Thinking with Images improves fine-grained VQA for MLLMs by emphasizing visual cues. However, tool-augmented methods depend on the capacity of grounding, which remains unreliable for MLLMs. In parallel, attention-driven methods to crop the…

Style transfer driven by text prompts paved a new path for creatively stylizing the images without collecting an actual style image. Despite having promising results, with text-driven stylization, the user has no control over the…

Diffusion-based text-to-image generation models have demonstrated strong performance in terms of image quality and diversity. However, they still struggle to generate images that accurately reflect the number of objects specified in the…

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can…

Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation…

Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle…

Text-to-image diffusion models (T2I DMs), represented by Stable Diffusion, which generate highly realistic images based on textual input, have been widely used, but their flexibility also makes them prone to misuse for producing harmful or…