Stay updated with the latest research and technology news
arXiv:2502.17629v4 Announce Type: replace Abstract: The palette sparsification theorem (PST) of Assadi, Chen, and Khanna (SODA 2019) states that in every graph $G$ with maximum...
arXiv:2503.00344v3 Announce Type: replace Abstract: This paper presents an algorithm to improve state estimation for legged robots. Among existing model-based state estimation methods for legged...
arXiv:2503.01544v2 Announce Type: replace Abstract: It is well understood that different neural network architectures are suited to different tasks, but is there always a single...
arXiv:2503.01805v2 Announce Type: replace Abstract: Transformers have revolutionized the field of machine learning. In particular, they can be used to solve complex algorithmic problems, including...
arXiv:2503.02623v5 Announce Type: replace Abstract: A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We...
arXiv:2503.07804v5 Announce Type: replace Abstract: We undertake a Shannon theoretic study of the problem of communicating bit streams over a 3-user quantum interference channel (QIC)...
arXiv:2503.08023v3 Announce Type: replace Abstract: The ability of the deep learning model to recognize when a sample falls outside its learned distribution is critical for...
arXiv:2503.14957v5 Announce Type: replace Abstract: In this work we present Knowledge Module Learning (KML) to understand and reason over procedural tasks that requires models to...
arXiv:2503.15149v2 Announce Type: replace Abstract: Accurate prediction of many-body dispersion (MBD) interactions is essential for understanding the van der Waals forces that govern the behavior...
arXiv:2503.15188v2 Announce Type: replace Abstract: The numerical accuracy of particle-based approximations in Smoothed Particle Hydrodynamics (SPH) is significantly affected by the spatial uniformity of particle...
arXiv:2504.00753v2 Announce Type: replace Abstract: Promoting the connectivity of curvilinear structures, such as neuronal processes in biomedical scans and blood vessels in CT images, remains...
arXiv:2504.05978v3 Announce Type: replace Abstract: Reinforcement learning (RL) is a powerful framework for decision-making in uncertain environments, but it often requires large amounts of data...
arXiv:2504.09956v2 Announce Type: replace Abstract: Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally...
arXiv:2504.10258v3 Announce Type: replace Abstract: Document Reading Order Recovery is a fundamental task in document image understanding, playing a pivotal role in enhancing Retrieval-Augmented Generation...
arXiv:2504.12007v4 Announce Type: replace Abstract: Recent advances in generative artificial intelligence, particularly large language models (LLMs), have opened new opportunities for enhancing recommender systems (RecSys)....
arXiv:2504.12461v4 Announce Type: replace Abstract: Trust is a fundamental concept in human decision-making and collaboration that has long been studied in philosophy and psychology. However,...
arXiv:2504.14174v2 Announce Type: replace Abstract: This position paper argues that the next generation of artificial intelligence in meteorological and climate sciences must transition from fragmented...
arXiv:2504.14569v5 Announce Type: replace Abstract: Large language models (LLMs) exhibit remarkable performance across various natural language processing tasks but suffer from immense computational and memory...
arXiv:2504.17229v2 Announce Type: replace Abstract: This paper presents a novel scheme to efficiently compress Light Detection and Ranging~(LiDAR) point clouds, enabling high-precision 3D scene archives,...
arXiv:2504.18903v3 Announce Type: replace Abstract: Recently, H(div)-conforming DG type methods coupled with Runge-Kutta (RK) time stepping have been widely employed for simulating high Reynolds number...
arXiv:2504.19373v4 Announce Type: replace Abstract: Recent advances in multi-modal large reasoning models (MLRMs) have shown significant ability to interpret complex visual content. While these models...
arXiv:2504.19660v2 Announce Type: replace Abstract: Mixture of Experts (MoE) has emerged as a promising paradigm for scaling model capacity while preserving computational efficiency, particularly in...
arXiv:2505.03953v2 Announce Type: replace Abstract: When solving optimization problems under uncertainty with contextual data, utilizing machine learning to predict the uncertain parameters' values is a...
arXiv:2505.05740v2 Announce Type: replace Abstract: This paper introduces the first globally optimal algorithm for the empirical risk minimization problem of two-layer maxout and ReLU networks,...