Stay updated with the latest research and technology news
arXiv:2508.03565v2 Announce Type: replace Abstract: Key-value stores underpin a wide range of applications due to their simplicity and efficiency. Log-Structured Merge Trees (LSM-trees) dominate as...
arXiv:2508.04655v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate strong capabilities in broad knowledge representation, yet they are inherently deficient in pixel-level perceptual understanding....
arXiv:2508.05470v4 Announce Type: replace Abstract: We examine, analyze, and compare four representative creativity measures--perplexity, LLM-as-a-Judge, the Creativity Index (CI; measuring n-gram overlap with web corpora),...
arXiv:2508.07286v3 Announce Type: replace Abstract: Accurate information extraction from specialized texts is a critical challenge for automated rule checking (ARC) in the architecture, engineering, and...
arXiv:2508.12216v2 Announce Type: replace Abstract: Feature lifting has emerged as a crucial component in 3D scene understanding, enabling the attachment of rich image feature descriptors...
arXiv:2508.16438v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing...
arXiv:2508.16922v2 Announce Type: replace Abstract: Capsule Network (CapsNet) has demonstrated significant potential in visual recognition by capturing spatial relationships and part-whole hierarchies for learning equivariant...
arXiv:2508.21155v2 Announce Type: replace Abstract: We consider parameterized variational inverse problems that are constrained by partial differential equations (PDEs). We seek to efficiently compute the...
arXiv:2509.00179v3 Announce Type: replace Abstract: Optimization under uncertainty is a fundamental problem in learning and decision-making, particularly in multi-agent systems. Previously, Feldman, Kalai, and Tennenholtz...
arXiv:2509.00183v3 Announce Type: replace Abstract: Data-driven modeling of constrained multibody dynamics remains challenged by (i) the training cost of Neural ODEs, which typically require backpropagation...
arXiv:2509.00778v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) require highly efficient matrix multiplication engines for complex computations. This paper presents a systolic array architecture...
arXiv:2509.00923v2 Announce Type: replace Abstract: Monte Carlo Counterfactual Regret Minimization (MCCFR) has emerged as a cornerstone algorithm for solving extensive-form games, but its integration with...
arXiv:2509.02072v4 Announce Type: replace Abstract: The automatic classification of occupational accident reports is pivotal for workplace safety analysis but is persistently hindered by severe class...
arXiv:2509.06350v2 Announce Type: replace Abstract: Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses...
arXiv:2509.09332v3 Announce Type: replace Abstract: Recent advances in multimodal large language models (MLLMs) have opened new opportunities for embodied intelligence, enabling multimodal understanding, reasoning, and...
arXiv:2509.10643v2 Announce Type: replace Abstract: Structured perturbation results for invariant subspaces of $\Delta$-Hermitian and Hamiltonian matrices are provided. The invariant subspaces under consideration are associated...
arXiv:2509.10782v2 Announce Type: replace Abstract: Generative artificial intelligence (GenAI) is rapidly entering K-12 classrooms worldwide, initiating urgent debates about its potential to either reduce or...
arXiv:2509.12626v2 Announce Type: replace Abstract: Agentic workflows promise efficiency, but adoption hinges on whether people can align systems that act on their behalf with their...
arXiv:2509.14427v2 Announce Type: replace Abstract: Information retrieval with compact binary embeddings, also referred to as hashing, is crucial for scalable fast search applications, yet state-of-the-art...
arXiv:2509.14586v5 Announce Type: replace Abstract: Data assimilation (DA) integrates observational data with numerical models to improve the prediction of complex physical systems. However, traditional DA...
arXiv:2509.14979v3 Announce Type: replace Abstract: Using Large Language Models (LLMs) to generate semantic features has been demonstrated as a powerful paradigm for enhancing Sequential Recommender...
arXiv:2509.15613v2 Announce Type: replace Abstract: We extend our work on a novel indoor positioning system (IPS) for autonomous mobile robots (AMRs) based on radar sensing...
arXiv:2509.17562v3 Announce Type: replace Abstract: Modern computer vision is converging on a closed loop in which perception, reasoning and generation mutually reinforce each other. However,...
arXiv:2509.17641v2 Announce Type: replace Abstract: Even without directly hearing sounds, humans can effortlessly reason about auditory properties, such as pitch, loudness, or sound-source associations, drawing...