Stay updated with the latest research and technology news
arXiv:2410.12985v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in medical fields. In mental health support, the early identification of linguistic markers...
arXiv:2410.14581v5 Announce Type: replace Abstract: Attention mechanisms have revolutionized several domains of artificial intelligence, such as natural language processing and computer vision, by enabling models...
arXiv:2410.20408v3 Announce Type: replace Abstract: This paper introduces a novel tangential-normal ($t$-$n$) decomposition for finite element differential forms, presenting a new framework for constructing bases...
arXiv:2410.22307v3 Announce Type: replace Abstract: The ever-increasing size of open-source Large Language Models (LLMs) renders local deployment impractical for individual users. Decentralized computing has emerged...
arXiv:2411.02843v3 Announce Type: replace Abstract: Photoacoustic imaging (PAI) represents an innovative biomedical imaging modality that harnesses the advantages of optical resolution and acoustic penetration depth...
arXiv:2411.06403v2 Announce Type: replace Abstract: We introduce a practical circuit-complexity model for fixed-precision neural networks to explain and overcome a persistent learnability barrier in impartial...
arXiv:2411.06501v2 Announce Type: replace Abstract: We study the regret in stochastic Multi-Armed Bandits (MAB) with multiple agents that communicate over an arbitrary connected communication graph....
arXiv:2411.10701v2 Announce Type: replace Abstract: Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is...
arXiv:2411.12433v2 Announce Type: replace Abstract: In a variety of domains, from robotics to finance, Quality-Diversity algorithms have been used to generate collections of both diverse...
arXiv:2411.16665v2 Announce Type: replace Abstract: Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or a few annotated...
arXiv:2411.17982v3 Announce Type: replace Abstract: We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input....
arXiv:2411.18037v3 Announce Type: replace Abstract: Breaking a norm elicits both material and emotional consequences, yet how this coupling arose evolutionarily remains unclear. We investigate this...
arXiv:2412.03205v4 Announce Type: replace Abstract: The current evaluation of mathematical skills in LLMs is limited, as existing benchmarks are either relatively small, primarily focus on...
arXiv:2412.04291v2 Announce Type: replace Abstract: Recent advancements have highlighted that large language models (LLMs), when given a small set of task-specific examples, demonstrate remarkable proficiency,...
arXiv:2412.09606v2 Announce Type: replace Abstract: Given that visual foundation models (VFMs) are trained on extensive datasets but often limited to 2D images, a natural question...
arXiv:2412.13526v3 Announce Type: replace Abstract: Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this...
arXiv:2412.20727v4 Announce Type: replace Abstract: Multivariate long-term time series forecasting aims to predict future sequences by utilizing historical observations, with a core focus on modeling...
arXiv:2501.04052v3 Announce Type: replace Abstract: The recently introduced NVFP4 format demonstrates remarkable performance and memory benefits for quantized large language model (LLM) inference. However, we...
arXiv:2501.05032v2 Announce Type: replace Abstract: This paper explores the advancements in making large language models (LLMs) more human-like. We focus on techniques that enhance natural...
arXiv:2501.07047v4 Announce Type: replace Abstract: Homomorphic Encryption (HE) provides strong data privacy for cloud services but at the cost of prohibitive computational overhead. While GPUs...
arXiv:2501.07114v2 Announce Type: replace Abstract: Compositional Zero-Shot Learning (CZSL) seeks to recognize unseen state-object pairs by recombining primitives learned from seen compositions. Despite recent progress...
arXiv:2501.07809v2 Announce Type: replace Abstract: We address the neutral inclusion problem with imperfect boundary conditions, focusing on designing interface functions for inclusions of arbitrary shapes....
arXiv:2501.08907v2 Announce Type: replace Abstract: Offline Reinforcement Learning (RL) faces a fundamental challenge of extrapolation errors caused by out-of-distribution (OOD) actions. Implicit Q-Learning (IQL) employs...
arXiv:2501.13448v2 Announce Type: replace Abstract: This paper introduces Localized Bipartite Match Graph Attention Q-Learning (BMG-Q), a novel Multi-Agent Reinforcement Learning (MARL) algorithm framework tailored for...