Related papers: ZSMILES: an approach for efficient SMILES storage …
Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…
Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs.…
Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and…
Background and objective: Sharing of medical data is required to enable the cross-agency flow of healthcare information and construct high-accuracy computer-aided diagnosis systems. However, the large sizes of medical datasets, the massive…
Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive…
The rapid development of tools for acquisition and storage of information has lead to the formation of enormous medical databases. The large quantity of data definitely surpasses the abilities of humans for efficient usage without…
Discovering materials with desirable properties in an efficient way remains a significant problem in materials science. Many studies have tackled this problem by using different sets of information available about the materials. Among them,…
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…
Despite remarkable advancements in pixel-level medical image perception, existing methods are either limited to specific tasks or heavily rely on accurate bounding boxes or text labels as input prompts. However, the medical knowledge…
Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…
Small molecules in biological samples are studied to provide information about disease states, environmental toxins, natural product drug discovery, and many other applications. The primary window into the composition of small molecule…
Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by…
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream video analysis tasks. In this paper, we propose a Masked…
Exa-scale simulations are on the horizon but almost no new design for the output has been proposed in recent years. In simulations using individual time steps, the traditional snapshots are over resolving particles/cells with large time…
An important topic in medical research is the process of improving the images obtained from medical devices. As a consequence, there is also a need to improve medical image resolution and analysis. Another issue in this field is the large…
In-context learning (ICL) with Large Vision Models (LVMs) presents a promising avenue in medical image segmentation by reducing the reliance on extensive labeling. However, the ICL performance of LVMs highly depends on the choices of visual…
High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency.…
In the coming era of exascale supercomputing, in-situ visualization will be a crucial approach for reducing the output data size. A problem of in-situ visualization is that it loses interactivity if a steering method is not adopted. In this…
The amount of medical images stored in hospitals is increasing faster than ever; however, utilizing the accumulated medical images has been limited. This is because existing content-based medical image retrieval (CBMIR) systems usually…
The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering…