Stay updated with the latest research and technology news
arXiv:2406.00410v3 Announce Type: replace Abstract: Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data,...
arXiv:2406.18265v3 Announce Type: replace Abstract: With the developments in machine learning, there has been a surge in interest and results focused on algorithms utilizing predictions,...
arXiv:2407.12138v3 Announce Type: replace Abstract: This work presents a framework for monocular 6D pose estimation of surgical instruments in open surgery, addressing challenges such as...
arXiv:2407.14129v3 Announce Type: replace Abstract: A large number of Deep Learning Weather Prediction (DLWP) architectures -- based on various backbones, including U-Net, Transformer, Graph Neural...
arXiv:2408.16536v2 Announce Type: replace Abstract: For safety-critical applications, it is crucial to audit 3D human pose estimators before deployment. Will the system break down if...
arXiv:2409.01763v4 Announce Type: replace Abstract: In this paper, we introduce FC-KAN, a Kolmogorov-Arnold Network (KAN) that leverages combinations of popular mathematical functions such as B-splines,...
arXiv:2409.10825v5 Announce Type: replace Abstract: Large Language Model (LLM)-based recommendation systems excel in delivering comprehensive suggestions by deeply analyzing content and user behavior. However, they...
arXiv:2409.12540v2 Announce Type: replace Abstract: Parallel coordinates plots (PCPs) are a widely used visualization method, particularly for exploratory analysis. Previous studies show that PCPs perform...
arXiv:2410.03129v3 Announce Type: replace Abstract: Large Language Models (LLMs) have greatly pushed forward advancements in natural language processing, yet their high memory and computational demands...
arXiv:2410.21214v2 Announce Type: replace Abstract: People increasingly use digital platforms to exchange resources in accordance with some policies stating what resources users offer and what...
arXiv:2411.08521v4 Announce Type: replace Abstract: Recently, researchers have begun to experiment with deep learning-based methods for detecting major depressive disor-der (MDD) using electroencephalogram (EEG) signals...
arXiv:2411.12703v4 Announce Type: replace Abstract: The rapid spread of misinformation, particularly through online platforms, underscores the urgent need for reliable detection systems. This study explores...
arXiv:2411.15494v2 Announce Type: replace Abstract: Gradient boosting decision forests, used by XGBoost or AdaBoost, offer higher accuracy and lower training times than decision trees for...
arXiv:2411.19089v2 Announce Type: replace Abstract: We consider a setting in which an evolving surface is implicitly characterized as the zero level of a level set...
arXiv:2412.00678v3 Announce Type: replace Abstract: Efficiently modeling large 2D contexts is essential for various fields including Giga-Pixel Whole Slide Imaging (WSI) and remote sensing. Transformer-based...
arXiv:2412.06646v4 Announce Type: replace Abstract: Recent advances in multimodal training have significantly improved the integration of image understanding and generation within a unified model. This...
arXiv:2412.10354v5 Announce Type: replace Abstract: We present NeuralOperator, an open-source Python library for operator learning. Neural operators generalize neural networks to maps between function spaces...
arXiv:2501.13428v5 Announce Type: replace Abstract: Large language models have achieved remarkable success in recent years, primarily due to self-attention. However, traditional Softmax attention suffers from...
arXiv:2502.00213v3 Announce Type: replace Abstract: Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite...
arXiv:2502.00655v2 Announce Type: replace Abstract: We study a regularization framework that combines a convex fidelity term with multiple $\ell_1$-based regularizers, each linked to a distinct...
arXiv:2502.03633v2 Announce Type: replace Abstract: In the preprocessing framework one is given a set of regions that one is allowed to preprocess to create some...
arXiv:2502.05179v4 Announce Type: replace Abstract: DiT models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale. High content...
arXiv:2502.07656v2 Announce Type: replace Abstract: We propose a general framework for causal Imitation Learning (IL) with hidden confounders, which subsumes several existing settings. Our framework...
arXiv:2502.13069v2 Announce Type: replace Abstract: AI agents are increasingly being deployed to automate tasks, often based on underspecified user instructions. Making unwarranted assumptions to compensate...