Federated Learning is a privacy-preserving decentralized approach for Machine Learning tasks. In industry deployments characterized by a limited number of entities possessing abundant data, the significance of a participant’s role in shaping the global model becomes pivotal given that participation in a federation incurs costs, and participants may expect compensation for their involvement. Additionally, the contributions of participants serve as a crucial means to identify and address potential malicious actors and free-riders. However, fairly assessing individual contributions remains […]

Ver mais

arXiv:2603.02059v1 Announce Type: new Abstract: Extreme weather events, such as windstorms and heatwaves, are driven by persistent atmospheric circulation patterns that evolve over several consecutive days. While traditional circulation-based studies often focus on instantaneous atmospheric states, capturing the temporal evolution, or trajectory, of these spatial fields is essential for characterizing rare and potentially impactful atmospheric behavior. However, performing an exhaustive similarity search on multi-decadal, continental-scale gridded datasets presents significant computational and memory challenges. In this paper, we propose […]

Ver mais

Reinforcement learning is increasingly deployed in domains where reward feedback is sparse, delayed, and entangled with long-horizon constraints, making reliable credit assignment difficult. A central development in recent work is the insertion of large language model modules directly into the reinforcement learning loop, not as peripheral interfaces but as components that alter trajectory generation and supervision. In these systems, language modules provide planning priors, structured reward shaping, process verification, synthetic world traces, and tool-memory context that reconfigure optimization […]

Ver mais

arXiv:2601.15432v1 Announce Type: new Abstract: Scientific research metadata is vital to ensure the validity, reusability, and cost-effectiveness of research efforts. The MEDFORD metadata language was previously introduced to simplify the process of writing and maintaining metadata for non-programmers. However, barriers to entry and usability remain, including limited automatic validation, difficulty of data transport, and user unfamiliarity with text file editing. To address these issues, we introduce MEDFORD-in-a-Box (MIAB), a documentation ecosystem to facilitate researcher adoption and earlier metadata […]

Ver mais

arXiv:2601.20013v1 Announce Type: new Abstract: This chapter offers a comprehensive introduction to the least-squares neural network (LSNN) method introduced in [14,16], for solving scalar first-order hyperbolic partial differential equations, specifically linear advection-reaction equations and nonlinear hyperbolic conservation laws. The LSNN method is built on an equivalent least-squares formulation of the underlying problem on an admissible solution set that accommodates discontinuous solutions. It employs ReLU neural networks (in place of finite elements) as the approximating functions, uses a carefully […]

Ver mais

arXiv:2602.04033v1 Announce Type: new Abstract: Recent studies evaluate the value orientation of large language models (LLMs) using adapted social surveys, typically by prompting models with survey questions and comparing their responses to average human responses. This paper identifies limitations in this methodology that, depending on the exact setup, can lead to both underestimating and overestimating the similarity of value orientation. Using the World Value Survey in three languages across five countries, we demonstrate that prompting methods (direct vs. […]

Ver mais

Suppose you have a set of k hash values, each n bits long. Can you compress the set into less than kn bits? It’s not possible to compress a list of hashes into less than kn bits, but you can hash a set into fewer bits. Suppose you have a set of 230, roughly a billion, 64-bit hashes. Sort the set and look at the size of gaps between elements. You might expect that consecutive items on the list are roughly 234 apart, […]

Ver mais

In the U.S. digital economy, small and medium-sized businesses (SMBs) and creators in remote regions face structural disadvantages in access to integrated advertising and incentive platforms, largely due to accelerating privacy regulations and the fragmentation of cross channel datasets. This paper proposes a unified federated and differentially private measurement framework that integrates Topics/Protected Audience, Attribution Reporting, and SKAdNetwork, aiming to achieve privacy-preserving incentive optimization and cross-channel effectiveness measurement for web and mobile environments. The framework prioritizes compliant data […]

Ver mais