相关论文: Cross-Attention Head Position Patterns Can Align w…

Enabling generative models to decompose visual concepts from a single image is a complex and challenging problem. In this paper, we study a new and challenging task, customized concept decomposition, wherein the objective is to leverage…

As black-box AI-driven decision-making systems become increasingly widespread in modern document processing workflows, improving their transparency and reliability has become critical, especially in high-stakes applications where biases or…

Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both…

Despite excelling on multimodal benchmarks, vision-language models (VLMs) largely remain a black box. In this paper, we propose a novel interpretability framework to systematically analyze the internal mechanisms of VLMs, focusing on the…

Large-scale text-to-image models that can generate high-quality and diverse images based on textual prompts have shown remarkable success. These models aim ultimately to create complex scenes, and addressing the challenge of multi-subject…

Large-scale diffusion models have made significant advances in image generation, particularly through cross-attention mechanisms. While cross-attention has been well-studied in text-to-image tasks, their interpretability in image-to-image…

Over the past decade, most methods in visual place recognition (VPR) have used neural networks to produce feature representations. These networks typically produce a global representation of a place image using only this image itself and…

We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose estimation, and different frameworks, such as one-stage or…

In this work, we address the challenging task of referring segmentation. The query expression in referring segmentation typically indicates the target object by describing its relationship with others. Therefore, to find the target one…

As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and…

Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches…

Recent advancements in text-to-image generative models have demonstrated a remarkable ability to capture a deep semantic understanding of images. In this work, we leverage this semantic knowledge to transfer the visual appearance between…

Visual generation and understanding are two deeply interconnected aspects of human intelligence, yet they have been traditionally treated as separate tasks in machine learning. In this paper, we propose Jodi, a diffusion framework that…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

Visual relationship understanding has been studied separately in human-object interaction(HOI) detection, scene graph generation(SGG), and referring relationships(RR) tasks. Given the complexity and interconnectedness of these tasks, it is…

Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the symbols. We propose a…

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced…

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

We address the problem of generating long-horizon videos for robotic manipulation tasks. Text-to-video diffusion models have made significant progress in photorealism, language understanding, and motion generation but struggle with…

While image captioning through machines requires structured learning and basis for interpretation, improvement requires multiple context understanding and processing in a meaningful way. This research will provide a novel concept for…