Stay updated with the latest research and technology news
arXiv:2505.07156v2 Announce Type: replace Abstract: We present a field-of-values (FOV) analysis for preconditioned nonsymmetric saddle-point linear systems, where zero is included in the field of...
arXiv:2504.19903v4 Announce Type: replace Abstract: In practical federated learning (FL), the large communication overhead between clients and the server is often a significant bottleneck. Gradient...
arXiv:2504.19715v2 Announce Type: replace Abstract: Complex mechanical systems such as vehicle powertrains are inherently subject to multiple nonlinearities and uncertainties arising from parametric variations. Modeling...
arXiv:2504.16956v3 Announce Type: replace Abstract: Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of cellular heterogeneity, but its complexity, which is marked by high dimensionality, sparsity,...
arXiv:2504.13898v2 Announce Type: replace Abstract: Our work focuses on the social reasoning capabilities of foundation models for real-world human-robot interactions. We introduce the Social Human...
arXiv:2504.13811v5 Announce Type: replace Abstract: WebShell attacks - where adversaries implant malicious scripts on web servers - remain a persistent threat. Prior machine-learning and deep-learning...
arXiv:2504.13363v2 Announce Type: replace Abstract: Integrating sensing and communication (ISAC) can help overcome the challenges of limited spectrum and expensive hardware, leading to improved energy...
arXiv:2504.13204v2 Announce Type: replace Abstract: 3D Gaussian Splatting reconstructs scenes by starting from a sparse Structure-from-Motion initialization and refining under-reconstructed regions. This process is slow,...
arXiv:2504.10793v3 Announce Type: replace Abstract: Imagine placing your smartphone on a table in a noisy restaurant and clearly capturing the voices of friends seated around...
arXiv:2504.09006v3 Announce Type: replace Abstract: We initiate the study of structured Stackelberg games, a novel form of strategic interaction between a leader and a follower...
arXiv:2504.05592v3 Announce Type: replace Abstract: In recent years, the evolution of modern power grids has been driven by the growing integration of remotely controlled grid...
arXiv:2504.04988v2 Announce Type: replace Abstract: Recent progress in VLMs has demonstrated impressive capabilities across a variety of tasks in the natural image domain. Motivated by...
arXiv:2503.16743v5 Announce Type: replace Abstract: We introduce an increasing-complexity, open-ended, and human-agnostic metric to evaluate foundational and frontier AI models in the context of Artificial...
arXiv:2503.09663v3 Announce Type: replace Abstract: Operating system (OS) kernel tuning is a critical yet challenging problem for performance optimization, due to the large configuration space,...
arXiv:2503.07869v3 Announce Type: replace Abstract: Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.g., sparse training data...
arXiv:2503.05696v4 Announce Type: replace Abstract: Many reinforcement learning (RL) algorithms are impractical for training in operational systems or computationally expensive high-fidelity simulations, as they require...
arXiv:2503.05587v2 Announce Type: replace Abstract: Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustness...
arXiv:2503.01605v2 Announce Type: replace Abstract: Soybean and cotton are major drivers of many countries' agricultural sectors, offering substantial economic returns but also facing persistent challenges...
arXiv:2502.13022v2 Announce Type: replace Abstract: We develop a novel method for personalized off-policy learning in scenarios with unobserved confounding. Thereby, we address a key limitation...
arXiv:2502.12594v3 Announce Type: replace Abstract: Model pruning is an effective approach for compressing large language models (LLMs). However, this process often leads to significant degradation...
arXiv:2502.12530v3 Announce Type: replace Abstract: As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies...
arXiv:2502.12022v5 Announce Type: replace Abstract: Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR)...
arXiv:2502.04667v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) training has markedly advanced the reasoning capabilities of large language models (LLMs), yet the mechanisms by which CoT...
arXiv:2501.15253v3 Announce Type: replace Abstract: The rapid advancement of Generative Adversarial Networks (GANs) and diffusion models has enabled the creation of highly realistic synthetic images,...