Stay updated with the latest research and technology news
arXiv:2505.08145v2 Announce Type: replace Abstract: Almost all existing hierarchical federated learning (FL) models are limited to two aggregation layers, restricting scalability and flexibility in complex,...
arXiv:2505.08417v2 Announce Type: replace Abstract: Grasping unknown objects in unstructured environments is a critical challenge for service robots, which must operate in dynamic, real-world settings...
arXiv:2505.10271v3 Announce Type: replace Abstract: We present a deep learning model for high-resolution probabilistic precipitation forecasting over an 8-hour horizon in Europe, overcoming the limitations...
arXiv:2505.10685v2 Announce Type: replace Abstract: 3D semantic occupancy prediction is essential for achieving safe, reliable autonomous driving and robotic navigation. Compared to camera-only perception systems,...
arXiv:2505.11304v2 Announce Type: replace Abstract: Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics...
arXiv:2505.11771v2 Announce Type: replace Abstract: Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative...
arXiv:2505.11839v2 Announce Type: replace Abstract: Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating...
arXiv:2505.12185v5 Announce Type: replace Abstract: Evaluating the programming robustness of large language models (LLMs) is paramount for ensuring their reliability in AI-based software development. However,...
arXiv:2505.12641v3 Announce Type: replace Abstract: Single image reflection separation aims to separate the transmission and reflection layers from a mixed image. Existing methods typically combine...
arXiv:2505.13766v3 Announce Type: replace Abstract: Software Quality Assurance (SQA) is critical for delivering reliable, secure, and efficient software products. The Software Quality Assurance Process aims...
arXiv:2505.14105v3 Announce Type: replace Abstract: Vision models pretrained on large-scale RGB natural image datasets are widely reused for electron microscopy image segmentation. In electron microscopy,...
arXiv:2505.14462v2 Announce Type: replace Abstract: As vision-language models (VLMs) become increasingly integrated into daily life, the need for accurate visual culture understanding is becoming critical....
arXiv:2505.15008v2 Announce Type: replace Abstract: Selective classification enhances the reliability of predictive models by allowing them to abstain from making uncertain predictions. In this work,...
arXiv:2505.18487v2 Announce Type: replace Abstract: Learning effective visual representations for robotic manipulation remains a fundamental challenge due to the complex body dynamics involved in action...
arXiv:2505.19645v4 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success across many applications, with Mixture of Experts (MoE) models demonstrating great potential....
arXiv:2505.19712v3 Announce Type: replace Abstract: This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to...
arXiv:2505.21936v4 Announce Type: replace Abstract: Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect...
arXiv:2505.22286v3 Announce Type: replace Abstract: Unmanned aerial vehicle (UAV) is regarded as a key enabling platform for low-altitude economy, due to its advantages such as...
arXiv:2505.23522v3 Announce Type: replace Abstract: Existing benchmarks for multimodal learning in Earth science offer limited, siloed coverage of Earth's spheres and their cross-sphere interactions, typically...
arXiv:2505.24440v3 Announce Type: replace Abstract: We compare the total capital efficiency of secure restaking and Proof-of-Stake (PoS) protocols. First, we consider the sufficient condition for...
arXiv:2506.00494v2 Announce Type: replace Abstract: The internal structure of the Fin-Ray fingers plays a significant role in their adaptability and grasping performance. However, modeling the...
arXiv:2506.02634v5 Announce Type: replace Abstract: Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially...
arXiv:2506.02873v4 Announce Type: replace Abstract: Persuasion is a powerful capability of large language models (LLMs) that both enables beneficial applications (e.g. helping people quit smoking)...
arXiv:2506.03407v2 Announce Type: replace Abstract: We present MS-Splatting -- a multi-spectral 3D Gaussian Splatting (3DGS) framework that is able to generate multi-view consistent novel views...