Related papers: Attention Overlap Is Responsible for The Entity Mi…
Text-to-image diffusion models have shown great success in generating high-quality text-guided images. Yet, these models may still fail to semantically align generated images with the provided text prompts, leading to problems like…
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…
Diffusion-based text-to-image models have rapidly gained popularity for their ability to generate detailed and realistic images from textual descriptions. However, these models often reflect the biases present in their training data,…
The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention…
Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…
Diffusion models have revolted the field of text-to-image generation recently. The unique way of fusing text and image information contributes to their remarkable capability of generating highly text-related images. From another…
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 convincing images following an input text prompt. The goal of image…
Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a causal analysis in…
While text-to-image diffusion models can generate highquality images from textual descriptions, they generally lack fine-grained control over the visual composition of the generated images. Some recent works tackle this problem by training…
Recently, the task of distantly supervised (DS) ultra-fine entity typing has received significant attention. However, DS data is noisy and often suffers from missing or wrong labeling issues resulting in low precision and low recall. This…
This paper analyzes the impact of causal manner in the text encoder of text-to-image (T2I) diffusion models, which can lead to information bias and loss. Previous works have focused on addressing the issues through the denoising process.…
Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often…
Recently, text-to-image generation with diffusion models has made significant advancements in both higher fidelity and generalization capabilities compared to previous baselines. However, generating holistic multi-view consistent images…
We are witnessing rapid progress in automatically generating and manipulating 3D assets due to the availability of pretrained text-image diffusion models. However, time-consuming optimization procedures are required for synthesizing each…
Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual text prompts and…
Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical challenge for diffusion-based models. Existing methods…
Text-to-image diffusion models have drawn significant attention for their ability to generate diverse and high-fidelity images. However, when generating from multi-concept prompts, one concept token often dominates the generation,…
Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…
Text-to-image (T2I) customization empowers users to adapt the T2I diffusion model to new concepts absent in the pre-training dataset. On this basis, capturing multiple new concepts from a single image has emerged as a new task, allowing the…
Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering…