Related papers: Squeezing Capacity from Multimodal Large Language …

In the past five years, research has shifted from traditional Machine Learning (ML) and Deep Learning (DL) approaches to leveraging Large Language Models (LLMs) , including multimodality, for data augmentation to enhance generalization, and…

Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…

Diffusion-based models have demonstrated impressive capabilities for text-to-image generation and are expected for personalized applications of subject-driven generation, which require the generation of customized concepts with one or a few…

This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…

Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Transformers, recent…

The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and…

Recent image generation approaches often address subject, style, and structure-driven conditioning in isolation, leading to feature entanglement and limited task transferability. In this paper, we introduce 3SGen, a task-aware unified…

Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we…

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…

Denoising Diffusion models have shown remarkable performance in generating diverse, high quality images from text. Numerous techniques have been proposed on top of or in alignment with models like Stable Diffusion and Imagen that generate…

Progress in image generation raises significant public security concerns. We argue that fake image detection should not operate as a "black box". Instead, an ideal approach must ensure both strong generalization and transparency. Recent…

Recent advancements in text-to-image (T2I) generative models have shown remarkable capabilities in producing diverse and imaginative visuals based on text prompts. Despite the advancement, these diffusion models sometimes struggle to…

Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it…

Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often…

The remarkable success of diffusion models in text-to-image generation has sparked growing interest in expanding their capabilities to a variety of multi-modal tasks, including image understanding, manipulation, and perception. These tasks…

Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand,…

Multimodal Large Language Models (MLLMs) have achieved strong performance on general visual benchmarks but struggle with out-of-distribution (OOD) tasks in specialized domains such as medical imaging, where labeled data is limited and…

This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to…

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…

Subject-driven image generation (SDIG) aims to manipulate specific subjects within images while adhering to textual instructions, a task crucial for advancing text-to-image diffusion models. SDIG requires reconciling the tension between…