Related papers: Medical Image Spatial Grounding with Semantic Samp…
Vision-language models typically reason over post-ISP RGB images, although RGB rendering can clip, suppress, or quantize sensor evidence before inference. We study whether grounding improves when the visual interface is moved closer to the…
It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language…
Medical large vision-language models (LVLMs) have demonstrated promising performance across various single-image question answering (QA) benchmarks, yet their capability in processing multi-image clinical scenarios remains underexplored.…
Vision language models (VLMs) can simultaneously reason about images and texts to tackle many tasks, from visual question answering to image captioning. This paper focuses on map parsing, a novel task that is unexplored within the VLM…
Vision-Language Models (VLMs) excel at describing visual scenes, yet struggle to translate perception into precise, grounded actions. We investigate whether providing VLMs with both the visual frame and the symbolic representation of the…
Artificial Intelligence models have demonstrated significant success in diagnosing skin diseases, including cancer, showing the potential to assist clinicians in their analysis. However, the interpretability of model predictions must be…
Spatio-physical reasoning, a foundation capability for understanding the real physics world, is a critical step towards building robust world models. While recent vision language models (VLMs) have shown remarkable progress in specialized…
Point cloud segmentation is central to autonomous driving and 3D scene understanding. While voxel- and point-based methods dominate recent research due to their compatibility with deep architectures and ability to capture fine-grained…
Recent advances in vision-language models (VLMs) have led to improved performance on tasks such as visual question answering and image captioning. Consequently, these models are now well-positioned to reason about the physical world,…
Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…
Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an…
Medical image segmentation (MIS) is a fundamental component of computer-assisted diagnosis and clinical decision support systems. Over the past decade, numerous architectures specifically tailored to medical imaging have emerged to address…
Comprehending 3D environments is vital for intelligent systems in domains like robotics and autonomous navigation. Voxel grids offer a structured representation of 3D space, but extracting high-level semantic meaning remains challenging.…
Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models…
Recently, developing unified medical image segmentation models gains increasing attention, especially with the advent of the Segment Anything Model (SAM). SAM has shown promising binary segmentation performance in natural domains, however,…
Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…
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…
Vision-language pre-training (VLP) has great potential for developing multifunctional and general medical diagnostic capabilities. However, aligning medical images with a low signal-to-noise ratio (SNR) to reports with a high SNR presents a…
The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance,…
Visual agent models for automating human activities on Graphical User Interfaces (GUIs) have emerged as a promising research direction, driven by advances in large Vision Language Models (VLMs). A critical challenge in GUI automation is the…