Related papers: Attention, Please! PixelSHAP Reveals What Vision-L…
Medical reports with substantial information can be naturally complementary to medical images for computer vision tasks, and the modality gap between vision and language can be solved by vision-language matching (VLM). However, current…
Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…
Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or document analysis, due to perception limitations and visual fragmentation. To address these challenges,…
The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering,…
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition…
Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for safe semantic reasoning and decision-making. While recent VLMs demonstrate strong performance…
Diagrams play a crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and…
Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across a range of…
Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…
With the growing deployment of Vision-Language Models (VLMs), pre-trained on large image-text and video-text datasets, it is critical to equip users with the tools to discern when to trust these systems. However, examining how user trust in…
When answering questions about images, humans naturally point, label, and draw to explain their reasoning. In contrast, modern vision-language models (VLMs) such as Gemini-3-Pro and GPT-5 only respond with text, which can be difficult for…
Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…
Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements. Nevertheless, these models heavily rely on image-text pairs that capture only coarse and global information of an image, leading to a limitation in…
Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing methods refine negation understanding via fine-tuning CLIP's…
In recent years, the Shapley value and SHAP explanations have emerged as one of the most dominant paradigms for providing post-hoc explanations of black-box models. Despite their well-founded theoretical properties, many recent works have…
We introduce ViLAM, a novel method for distilling vision-language reasoning from large Vision-Language Models (VLMs) into spatial attention maps for socially compliant robot navigation. Unlike traditional methods that rely on expert…
Multimodal large language models (MLLMs) have demonstrated strong general-purpose capabilities in open-world visual comprehension. However, most existing MLLMs primarily focus on holistic, scene-level understanding, often overlooking the…
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current paradigm uses visual features as prompts to guide language…
In this paper, we present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs). Visual prompts allow users to interact through multi-modal…
Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data…