Related papers: New Developments in FormCalc 8.4

In this work, we propose a low-bit training framework for convolutional neural networks, which is built around a novel multi-level scaling (MLS) tensor format. Our framework focuses on reducing the energy consumption of convolution…

In this work, we quantize a trained Transformer machine language translation model leveraging INT8/VNNI instructions in the latest Intel$^\circledR$ Xeon$^\circledR$ Cascade Lake processors to improve inference performance while maintaining…

FEMSIM, a Fortran code, has been developed to simulate the fluctuation electron microscopy signal, the variance, V(k), from a model atomic structure. FEMSIM has been incorporated into a hybrid-reverse Monte Carlo code that combines an…

This research explores the development of multimodal vision-language models for image retrieval in low-resource languages, specifically Azerbaijani. Existing vision-language models primarily support high-resource languages, and fine-tuning…

Multi-modal image fusion (MMIF) enhances the information content of the fused image by combining the unique as well as common features obtained from different modality sensor images, improving visualization, object detection, and many more…

While the state-of-the-art for frame semantic parsing has progressed dramatically in recent years, it is still difficult for end-users to apply state-of-the-art models in practice. To address this, we present Frame Semantic Transformer, an…

High precision calculations in perturbative QFT often require evaluation of big collection of Feynman integrals. Complexity of this task can be greatly reduced via the usage of linear identities among Feynman integrals. Based on…

This paper introduces a novel lightweight computational framework for enhancing images under low-light conditions, utilizing advanced machine learning and convolutional neural networks (CNNs). Traditional enhancement techniques often fail…

The new software FEniCS-preCICE is a middle software layer, sitting in between the existing finite-element library FEniCS and the coupling library preCICE. The middle layer simplifies coupling (existing) FEniCS application codes to other…

Document Image Machine Translation (DIMT) aims to translate text within document images, facing generalization challenges due to limited training data and the complex interplay between visual and textual information. To address these…

Multi-modal named entity recognition (MNER) aims at identifying entity spans and recognizing their categories in social media posts with the aid of images. However, in dominant MNER approaches, the interaction of different modalities is…

DEMIRCI software aims to aid RFQ design efforts by making the process easy, fast and accurate. In this report, DEMIRCI 8-term potential results are compared with the results provided by other commercially available simulation software.…

We introduce Nemotron-Parse-1.1, a lightweight document parsing and OCR model that advances the capabilities of its predecessor, Nemoretriever-Parse-1.0. Nemotron-Parse-1.1 delivers improved capabilities across general OCR, markdown…

This manuscript is a collection of problems and solutions related to modeling the cryosphere using the finite element software FEniCS. Included is an introduction to the finite element method; solutions to a variety of problems in one, two,…

mlx-vis implements eight dimensionality reduction methods -- UMAP, t-SNE, PaCMAP, LocalMAP, TriMap, DREAMS, CNE, MMAE -- and NNDescent k-NN graph construction entirely in MLX for Apple Silicon Metal GPU. A built-in GPU renderer produces…

Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new minimal solvers for classical problems such as homography,…

Recent years have witnessed an increasing interest in image-text contrastive modeling, exemplified by models such as Contrastive Language-Image Pretraining (CLIP). In this paper, we propose the TernaryCLIP, a lightweight computational…

We present updates on the development of pySecDec, a toolbox to numerically evaluate parameter integrals in the context of dimensional regularization. We discuss difficulties with loop integrals in the special kinematic condition where the…

We provide an analysis of the structure of renormalisation scheme invariants for the case of $\phi^4$ theory, relevant in four dimensions. We give a complete discussion of the invariants up to four loops and include some partial results at…

Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy. Towards this…