60 papers
This paper proposes a Spatio-Temporal Attention Graph Neural Network (STA-GNN) that integrates conformal prediction to provide unsupervised, explainable, and drift-aware anomaly detection for Industrial Control Systems by modeling dynamic inter-dependencies across physical and network entities.
This paper presents a method for obtaining precise and inexpensive upper bounds on the condition number of Chebyshev filtered vectors, which is then used to implement an adaptive QR-factorization selection mechanism in the ChASE library that enhances performance without compromising accuracy.
This paper presents a retrieval-augmented language assistant designed to support unmanned aircraft safety assessments and regulatory compliance by grounding responses in authoritative sources to ensure traceable, auditable, and citation-driven decision support without replacing expert judgment.
This paper presents a comprehensive atlas of approximately 1.95 million cubic symmetric metamaterials derived from all 36 cubic space groups, revealing extreme mechanical properties like high bulk-to-shear ratios and negative Poisson's ratios, while introducing a 3D convolutional neural network surrogate model to accelerate the discovery and design of such architected materials.
TrinityDNA is a novel, bio-inspired foundational model that integrates structural feature capture, symmetry handling, multi-scale attention, and evolutionary training to efficiently model long DNA sequences, significantly advancing gene function prediction and regulatory discovery while introducing a new long-sequence CDS annotation benchmark.
This paper introduces and analyzes a divide-and-conquer algorithm for quantizing one-dimensional probability distributions, establishing a universal Wasserstein-1 error bound and demonstrating through numerical experiments that the method achieves optimal convergence rates while offering superior stability under arithmetic operations compared to existing schemes.
This paper presents a specialized lock-free work-stealing queue designed for a master-worker framework in mixed-integer programming solvers that leverages restricted concurrency assumptions to support native bulk operations and achieve constant-latency push performance, significantly outperforming general-purpose implementations like C++ Taskflow in batch processing scenarios.
This paper proposes TCR-EML, an explainable-by-design model that integrates prototype layers based on known biochemical binding mechanisms into protein-language model backbones to achieve competitive TCR-pMHC binding prediction accuracy while providing interpretable rationales superior to existing black-box approaches.
This paper introduces Quantifying Cross-Attention Interaction (QCAI), a novel post-hoc explainable AI method that interprets cross-attention mechanisms in encoder-decoder transformers to improve the understanding of TCR-pMHC binding, achieving state-of-the-art performance on the newly established TCR-XAI benchmark of 274 experimentally determined structures.
The paper introduces GMM-PIELM, a probabilistic adaptive sampling framework that significantly improves the accuracy and conditioning of Physics-Informed Extreme Learning Machines for stiff PDEs by autonomously concentrating basis function centers in high-error regions like shock fronts, achieving orders-of-magnitude lower errors than baseline methods while retaining rapid closed-form training speeds.
This paper presents an international expert review on the clinical integration and translational readiness of emerging foundation and agentic AI in computational pathology, moving beyond technical performance to address the economic, regulatory, and operational barriers hindering real-world adoption in patient care.
The paper introduces Ptychi-Evolve, an autonomous framework that leverages large language models and evolutionary mechanisms to automatically discover and evolve novel regularization algorithms for ptychography, achieving significant reconstruction quality improvements across diverse imaging datasets.
This paper provides a guide for NLP researchers and interdisciplinary scientists on popular digital molecular representations inspired by natural language processing and their applications in AI-driven chemistry and materials science.
This paper introduces CliqueFlowmer, an offline model-based optimization framework that integrates clique-based optimization with transformer and flow generation to effectively discover materials with superior target properties, outperforming traditional generative baselines.
This paper introduces AllScAIP, a scalable, attention-based machine-learning interatomic potential that leverages all-to-all node attention to effectively capture long-range interactions and achieve state-of-the-art accuracy across diverse molecular and material systems without relying on explicit physics-based terms.
This paper introduces a graph-based framework for Thermodynamical Material Networks (TMNs) that models circular economy material flows using dynamic energy and mass balances, proposes new circularity indicators, and validates the approach through numerical simulations of fluid and solid material systems.
MOOSEnger is a domain-specific AI agent that combines retrieval-augmented generation with deterministic, MOOSE-aware parsing and execution tools to automatically convert natural language into validated simulation inputs, achieving a 93% execution success rate on a diverse benchmark compared to just 8% for an LLM-only baseline.
This paper introduces VeNRA, a neuro-symbolic financial reasoning system that replaces probabilistic text retrieval with a strictly typed Universal Fact Ledger and employs an adversarially trained Sentinel model to audit execution traces, thereby eliminating hallucinations and arithmetic errors in high-stakes financial domains.
This paper demonstrates that treating an instrumented building floor as a physical reservoir computer, combined with a lightweight processing pipeline, enables robust, subject-independent footstep localization with sub-meter to meter-scale accuracy using floor vibration data.
FedEMA-Distill is a robust and communication-efficient federated learning framework that leverages server-side exponential moving average smoothing and ensemble knowledge distillation from compressed client logits to achieve superior accuracy, faster convergence, and Byzantine resilience under non-IID data conditions without requiring client-side software modifications.