arXiv:2601.12148v1 Announce Type: new Abstract: Malicious code in open-source repositories such as PyPI poses a growing threat to software supply chains. Traditional rule-based tools often overlook the semantic patterns in source code that are crucial for identifying adversarial components. Large language models (LLMs) show promise for software analysis, yet their use in interpretable and modular security pipelines remains limited. This paper presents LAMPS, a multi-agent system that employs collaborative LLMs to detect malicious PyPI packages. The system consists […]

Ver mais

“Is coding essential for UX Designers?” If I had a nickel for every time a mentee or someone asked me this very question, I’d probably have enough to buy a lifetime subscription to Figma. As a UX Designer who’s heavily dependent on research, I remember doing my due diligence and extensively scouring the internet, as well as asking my ADPList and LinkedIn mentors this exact same question! Now, as someone who’s done a LOT of primary and secondary […]

Ver mais

arXiv:2602.03895v1 Announce Type: new Abstract: Machine learning models trained on real-world data often inherit and amplify biases against certain social groups, raising urgent concerns about their deployment at scale. While numerous bias mitigation methods have been proposed, comparing the effectiveness of bias mitigation methods remains difficult due to heterogeneous datasets, inconsistent fairness metrics, isolated evaluation of vision versus multi-modal models, and insufficient hyperparameter tuning that undermines fair comparisons. We introduce NH-Fair, a unified benchmark for fairness without harm […]

Ver mais

Partial differential equations (PDEs) govern complex systems, yet neural operators often struggle to efficiently capture the long-range, nonlocal interactions inherent in their solution maps. We introduce Spectral Filtering Operator (SFO), a neural operator that parameterizes integral kernels using the Universal Spectral Basis (USB), a fixed, global orthonormal basis derived from the eigenmodes of the Hilbert matrix in spectral filtering theory. Motivated by our theoretical finding that the discrete Green’s functions of shift-invariant PDE discretizations exhibit spatial Linear Dynamical […]

Ver mais

arXiv:2602.10266v1 Announce Type: new Abstract: This chapter explores neural networks, topological data analysis, and topological deep learning techniques, alongside statistical Bayesian methods, for processing images, time series, and graphs to maximize the potential of artificial intelligence in the military domain. Throughout the chapter, we highlight practical applications spanning image, video, audio, and time-series recognition, fraud detection, and link prediction for graphical data, illustrating how topology-aware and uncertainty-aware models can enhance robustness, interpretability, and generalization.

Ver mais

arXiv:2601.16356v1 Announce Type: new Abstract: Large Language Model (LLM)-powered web GUI agents are increasingly automating everyday online tasks. Despite their popularity, little is known about how users’ preferences and values impact agents’ reasoning and behavior. In this work, we investigate how both explicit and implicit user preferences, as well as the underlying user values, influence agent decision-making and action trajectories. We built a controlled testbed of 14 common interactive web tasks, spanning shopping, travel, dining, and housing, each […]

Ver mais

Frontier AI systems increasingly train on specialized expert data, from clinical records to proprietary research to curated datasets, yet current training pipelines treat all samples identically. A Nobel laureate’s contribution receives the same weight as an unverified submission. We introduce ANML (Attribution-Native Machine Learning), a framework that weights training samples by four quality factors: gradient-based consistency (q), verification status (v), contributor reputation (r), and temporal relevance (T). By combining what the model observes (gradient signals) with what the […]

Ver mais

Wearable sensors enable continuous monitoring of human activity and physiological state, with applications in workplace health monitoring, occupational safety, sports performance analysis, and rehabilitation. However, effective use of these devices requires specialized data-processing algorithms and machine-learning (ML) methods. This work proposes a methodology for assessing workers’ physiological load using ML, combining accelerometer and photoplethysmography (PPG) signal processing. An ensemble Random Forest algorithm is used for activity recognition, while the KID-PPG deep learning model is applied for heart rate […]

Ver mais