Related papers: EasyRef: Omni-Generalized Group Image Reference fo…

Finetuned LLMs often exhibit poor uncertainty quantification, manifesting as overconfidence, poor calibration, and unreliable prediction results on test data or out-of-distribution samples. One approach commonly used in vision for…

In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges. This paper introduces an innovative…

Face recognition systems are increasingly vulnerable to morphing attacks, where a composite image is crafted to match multiple identities, enabling unauthorized access and identity fraud. Existing detection methods identify morphed images…

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently…

Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image editing remains a challenging problem, requiring precise…

Although Large Language Models (LLMs) have shown promise for human-like conversations, they are primarily pre-trained on text data. Incorporating audio or video improves performance, but collecting large-scale multimodal data and…

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…

Despite remarkable progress, existing multimodal large language models (MLLMs) are still inferior in granular visual recognition. Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a…

Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…

Diffusion models (DMs) have achieved state-of-the-art results for image synthesis tasks as well as density estimation. Applied in the latent space of a powerful pretrained autoencoder (LDM), their immense computational requirements can be…

Diffusion models have emerged as the leading approach for text-to-image generation. However, their iterative sampling process, which gradually morphs random noise into coherent images, introduces significant latency that limits their…

Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…

Style transfer involves transferring the style from a reference image to the content of a target image. Recent advancements in LoRA-based (Low-Rank Adaptation) methods have shown promise in effectively capturing the style of a single image.…

Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed…

Although diffusion models exhibit impressive generative capabilities, existing methods for stylized image generation based on these models often require textual inversion or fine-tuning with style images, which is time-consuming and limits…

Among the representation learning, the low-rank representation (LRR) is one of the hot research topics in many fields, especially in image processing and pattern recognition. Although LRR can capture the global structure, the ability of…

Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance…

This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training…

Deep neural networks have emerged as a powerful technique for learning representations from user-item interaction data in collaborative filtering (CF) for recommender systems. However, many existing methods heavily rely on unique user and…