arXiv:2506.16230v2 Announce Type: replace-cross Abstract: Risk measures such as Conditional Value-at-Risk (CVaR) focus on extreme losses, where scarce tail data makes model error unavoidable. To hedge misspecification, one evaluates worst-case tail risk over an ambiguity set. Using Extreme Value Theory (EVT), we derive first-order asymptotics for worst-case tail risk for a broad class of tail-risk measures under standard ambiguity sets, including Wasserstein balls and $phi$-divergence neighborhoods. We show that robustification can alter the nominal tail asymptotic scaling as […]

Ver mais

Just read through this new systematic review (arXiv:2601.09334) on Serverless for HPC/AI. It’s a solid read if you’re dealing with infrastructure scaling. The TL;DR: Static Allocation is breaking: The paper argues that rigid GPU clusters can’t handle modern “bursty” AI workloads efficiently. You either over-provision (waste money) or under-provision (crash during spikes). Serverless is the fix: The industry is moving toward elastic, serverless execution models to survive the efficiency gap. We’ve been seeing this exact pattern in production. […]

Ver mais

arXiv:2601.00004v1 Announce Type: new Abstract: Depression is a major contributor to the mental-health burden in Nigeria, yet screening coverage remains limited due to low access to clinicians, stigma, and language barriers. Traditional tools like the Patient Health Questionnaire-9 (PHQ-9) were validated in high-income countries but may be linguistically or culturally inaccessible for low- and middle-income countries and communities such as Nigeria where people communicate in Nigerian Pidgin and more than 520 local languages. This study presents a novel […]

Ver mais

When we optimize responses using a reward model as a proxy for “goodness” in reinforcement learning, models sometimes learn to “hack” this proxy and output an answer that only “looks good” to it (because coming up with an answer that is actually good can be hard). The philosophy behind confessions is that we can train models to produce a second output — aka a “confession” — that is rewarded solely for honesty, which we will argue is less […]

Ver mais

arXiv:2601.09004v1 Announce Type: new Abstract: Agglomeration refers to the process of crystal clustering due to interparticle forces. Crystal agglomeration analysis from microscopic images is challenging due to the inherent limitations of two-dimensional imaging. Overlapping crystals may appear connected even when located at different depth layers. Because optical microscopes have a shallow depth of field, crystals that are in-focus and out-of-focus in the same image typically reside on different depth layers and do not constitute true agglomeration. To address […]

Ver mais

arXiv:2601.08033v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are the go-to model for graph data analysis. However, GNNs rely on two key operations – aggregation and update, which can pose challenges for low-latency inference tasks or resource-constrained scenarios. Simple Multi-Layer Perceptrons (MLPs) offer a computationally efficient alternative. Yet, training an MLP in a supervised setting often leads to suboptimal performance. Knowledge Distillation (KD) from a GNN teacher to an MLP student has emerged to bridge this gap. […]

Ver mais

Artificial intelligence systems are rapidly becoming integral to defense, intelligence, and critical infrastructure; yet, existing cybersecurity frameworks provide limited guidance for securing AI-specific components, such as model supply chains and training data pipelines. While Zero Trust Architecture (ZTA) offers a powerful foundation for modern cybersecurity, and while secure MLOps practices and ZT-adjacent controls for ML pipelines have emerged in practitioner literature, these efforts have not been integrated into a comprehensive framework that decomposes AI systems into distinct trust […]

Ver mais

arXiv:2602.03873v1 Announce Type: new Abstract: Emotion recognition from human speech is a critical enabler for socially aware conversational AI. However, while most prior work frames emotion recognition as a categorical classification problem, real-world affective states are often ambiguous, overlapping, and context-dependent, posing significant challenges for both annotation and automatic modeling. Recent large-scale audio language models (ALMs) offer new opportunities for nuanced affective reasoning without explicit emotion supervision, but their capacity to handle ambiguous emotions remains underexplored. At the […]

Ver mais

arXiv:2601.07965v1 Announce Type: new Abstract: When a model knows when it does not know, many possibilities emerge. The first question is how to enable a model to recognize that it does not know. A promising approach is to use confidence, computed from the model’s internal signals, to reflect its ignorance. Prior work in specific domains has shown that calibration can provide reliable confidence estimates. In this work, we propose a simple, effective, and universal training-free method that applies […]

Ver mais

arXiv:2601.08049v1 Announce Type: new Abstract: The increasing adoption of smart classroom technologies in higher education has mainly focused on automating attendance, with limited attention given to students’ emotional and cognitive engagement during lectures. This limits instructors’ ability to identify disengagement and adapt teaching strategies in real time. This paper presents SCASED (Smart Classroom Attendance System with Emotion Detection), an IoT-based system that integrates automated attendance tracking with facial emotion recognition to support classroom engagement monitoring. The system uses […]

Ver mais