Related papers: VIEScore: Towards Explainable Metrics for Conditio…

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

While text-to-image generation has been extensively studied, generating images from scene graphs remains relatively underexplored, primarily due to challenges in accurately modeling spatial relationships and object interactions. To fill…

High-quality source-target image pairs with precise editing instructions are essential for instruction-guided image editing, yet constructing such training triplets at scale remains costly. Recent pipelines often rely on vision-language…

Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a…

Achieving fine-grained controllability in human image synthesis is a long-standing challenge in computer vision. Existing methods primarily focus on either facial synthesis or near-frontal body generation, with limited ability to…

A fundamental component of human vision is our ability to parse complex visual scenes and judge the relations between their constituent objects. AI benchmarks for visual reasoning have driven rapid progress in recent years with…

Understanding realistic visual scene images together with language descriptions is a fundamental task towards generic visual understanding. Previous works have shown compelling comprehensive results by building hierarchical structures for…

The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a…

In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically…

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…

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels…

The rapid advancements in AI technologies have revolutionized the production of graphical content across various sectors, including entertainment, advertising, and e-commerce. These developments have spurred the need for robust evaluation…

Controllable Image Captioning (CIC) -- generating image descriptions following designated control signals -- has received unprecedented attention over the last few years. To emulate the human ability in controlling caption generation,…

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient…

Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly…

While Multimodal Large Language Models (MLLMs) have experienced significant advancement in visual understanding and reasoning, their potential to serve as powerful, flexible, interpretable, and text-driven models for Image Quality…

Visual instruction tuning is crucial for enhancing the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs). In this paper, we aim to investigate a fundamental question: ''what makes for good visual…

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to…

Vision--Language Models (VLMs) have demonstrated success across diverse applications, yet their potential to assist in relevance judgments remains uncertain. This paper assesses the relevance estimation capabilities of VLMs, including CLIP,…