arXiv:2602.04078v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success across a wide range of domains, significantly expanding the frontiers of what is achievable in artificial intelligence. Yet, despite these advances, critical challenges remain — most notably, ensuring robustness to small input perturbations and generalization to out-of-distribution data. These critical challenges underscore the need to understand the underlying fundamental principles that govern robustness and generalization. Among the theoretical tools available, Lipschitz continuity plays a pivotal role in […]

Ver mais

Hi everyone, Michael Reilly here. As March draws to a close—and we wrap up the month with an investigation into how NYC’s AI-powered bot tells people to break the law—I’ve been asking around the newsroom to find out what else has captured my colleagues’ interest and fascination over the last month. Below you’ll find an eclectic mix of the things that we read, play, listen to, and otherwise feed our brains with when we’re not heads down doing […]

Ver mais

Accurate localization of the seizure onset zone (SOZ) from intracranial EEG (iEEG) is essential for epilepsy surgery but is challenged by complex spatiotemporal seizure dynamics. We propose SpaTeoGL, a spatiotemporal graph learning framework for interpretable seizure network analysis. SpaTeoGL jointly learns window-level spatial graphs capturing interactions among iEEG electrodes and a temporal graph linking time windows based on similarity of their spatial structure. The method is formulated within a smooth graph signal processing framework and solved via an […]

Ver mais

arXiv:2505.17004v3 Announce Type: replace-cross Abstract: We propose a general framework for conditional sampling in PDE-based inverse problems, targeting the recovery of whole solutions from extremely sparse or noisy measurements. This is accomplished by a function-space diffusion model and plug-and-play guidance for conditioning. Our method first trains an unconditional, discretization-agnostic denoising model using neural operator architectures. At inference, we refine the samples to satisfy sparse observation data via a gradient-based guidance mechanism. Through rigorous mathematical analysis, we extend Tweedie’s […]

Ver mais

arXiv:2601.12343v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to predict human behavior. We propose a measure for evaluating how much knowledge a pretrained LLM brings to such a prediction: its equivalent sample size, defined as the amount of task-specific data needed to match the predictive accuracy of the LLM. We estimate this measure by comparing the prediction error of a fixed LLM in a given domain to that of flexible machine learning models trained […]

Ver mais

arXiv:2601.17048v1 Announce Type: new Abstract: Accurate characterization of silicon microstructures is essential for advancing microscale fabrication, quality control, and device performance. Traditional analysis using Scanning Electron Microscopy (SEM) often requires labor-intensive, manual evaluation of feature geometry, limiting throughput and reproducibility. In this study, we propose SiMiC: Context-Aware Silicon Microstructure Characterization Using Attention-Based Convolutional Neural Networks for Field-Emission Tip Analysis. By leveraging deep learning, our approach efficiently extracts morphological features-such as size, shape, and apex curvature-from SEM images, significantly […]

Ver mais

Neural networks often rely on spurious shortcuts for many epochs before discovering structured representations. However, the mechanism governing when this transition occurs and whether its timing can be predicted remains unclear. Prior work shows that gradient descent converges to low norm solutions and that neural networks exhibit simplicity bias, but neither explains the timescale of the transition from shortcut features to structured representations. We introduce the Norm-Hierarchy Transition (NHT) framework, which explains delayed representation learning as the slow […]

Ver mais

arXiv:2602.14423v1 Announce Type: cross Abstract: Data augmentation is one of the most widely used techniques to improve generalization in modern machine learning, often justified by its ability to promote invariance to label-irrelevant transformations. However, its theoretical role remains only partially understood. In this work, we propose an information-theoretic framework that systematically accounts for the effect of augmentation on generalization and invariance learning. Our approach builds upon mutual information-based bounds, which relate the generalization gap to the amount of […]

Ver mais

arXiv:2603.05647v1 Announce Type: new Abstract: People experiencing mental health crises frequently turn to open-ended generative AI (GenAI) chatbots such as ChatGPT for support. However, rather than providing immediate assistance, most GenAI chatbots are designed to respond to crisis situations in ways that minimize their developers’ liability, primarily through avoidance (e.g., refusing to engage beyond templated referrals to crisis hotlines). Withholding crisis support in these cases may harm users who have no viable alternatives and reduce their motivation to […]

Ver mais

arXiv:2601.15423v1 Announce Type: new Abstract: We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system clusters behavior windows into behavioral archetypes and uses binary confidence gating to activate archetype-based scoring only when confidence exceeds a threshold, falling back to baseline predictions when uncertain. We validate Lattice on recommendation systems (MovieLens), scientific time-series (LIGO), and financial markets, using LSTM and transformer backbones. On MovieLens with LSTM, Lattice achieves +31.9% […]

Ver mais