相关论文: Q-Align: Teaching LMMs for Visual Scoring via Disc…

The advent and proliferation of large multi-modal models (LMMs) have introduced new paradigms to computer vision, transforming various tasks into a unified visual question answering framework. Video Quality Assessment (VQA), a classic field…

This paper presents a summary of the VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models (LMMs), hosted as part of the ICCV 2025 Workshop on Visual Quality Assessment. The challenge aims to evaluate and enhance…

Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the…

This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggles in localizing an…

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…

Recently, multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence. In particular, vision-language MLLMs have been developed to generate not only text but also visual outputs from…

Multiple-choice questions (MCQs) are a widely used educational tool, particularly in domains such as visualization literacy that require broad conceptual coverage and support diverse real-world applications. However, designing high-quality…

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in…

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

Designing effective game tutorials is crucial for a smooth learning curve for new players, especially in games with many rules and complex core mechanics. Evaluating the effectiveness of these tutorials usually requires multiple iterations…

We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance…

Large Vision-Language Models (LVLMs) have shown strong performance across various multimodal tasks by leveraging the reasoning capabilities of Large Language Models (LLMs). However, processing visually complex and information-rich images,…

Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, how much visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong…

Assessing student's answers and in particular natural language answers is a crucial challenge in the field of education. Advances in machine learning, including transformer-based models such as Large Language Models(LLMs), have led to…

Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world…

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms…