Related papers: Interactive visualization of large molecular syste…
ASCRIBE-XR, a novel computational platform designed to facilitate the visualization and exploration of 3D volumetric data and mesh data in the context of synchrotron experiments, is described. Using Godot and PC-VR technologies, the…
Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alternative representations. While texture-based encodings such as Gramian Angular Fields (GAF)…
Most investigations into near-memory hardware accelerators for deep neural networks have primarily focused on inference, while the potential of accelerating training has received relatively little attention so far. Based on an in-depth…
Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…
Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the…
Processing of medical images such as MRI or CT presents unique challenges compared to RGB images typically used in computer vision. These include a lack of labels for large datasets, high computational costs, and metadata to describe the…
Optical Chemical Structure Recognition (OCSR) is essential for converting molecular images into machine-readable formats. While recent vision-language models (VLMs) have shown promise, their image-captioning approach often struggles with…
Event-based cameras offer unique advantages such as high temporal resolution, high dynamic range, and low power consumption. However, the massive storage requirements and I/O burdens of existing synthetic data generation pipelines and the…
Large Vision-Language Models (VLMs) deliver exceptional performance but require significant computational resources, limiting their deployment on mobile and edge devices. Smaller VLMs typically mirror design choices of larger models, such…
PlayMolecule Viewer is a web-based data visualization toolkit designed to streamline the exploration of data resulting from structural bioinformatics or computer-aided drug design efforts. By harnessing state-of-the-art web technologies…
Recent advances in Multi-modal Large Language Models (MLLMs) have shown significant progress in open-world Visual Question Answering (VQA). However, integrating visual information increases the number of processed tokens, leading to higher…
Compared to the first generation of deep neural networks, dominated by regular, compute-intensive kernels such as matrix multiplications (MatMuls) and convolutions, modern decoder-based transformers interleave attention, normalization, and…
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like…
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…
Dense Matrix Multiplication (MatMul) is arguably one of the most ubiquitous compute-intensive kernels, spanning linear algebra, DSP, graphics, and machine learning applications. Thus, MatMul optimization is crucial not only in…
Pore forming toxins (PFTs) are virulent proteins released by several species, including many strains of bacteria, to attack and kill host cells. In this article, we focus on the utility of molecular dynamics (MD) simulations and the…
In medical healthcare, obtaining detailed annotations is challenging, highlighting the need for robust Vision-Language Models (VLMs). Pretrained VLMs enable fine-tuning on small datasets or zero-shot inference, achieving performance…
With the development of high-speed electron detectors, four-dimensional scanning transmission electron microscopy (4D-STEM) has emerged as a powerful tool for characterizing microstructures in material science and life science. However, the…
Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training…
Biologists are leading current research on genome characterization (sequencing, alignment, transcription), providing a huge quantity of raw data about many genome organisms. Extracting knowledge from this raw data is an important process…