arXiv:2510.27400v1 Announce Type: cross Abstract: Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters. However, most existing methods focus on the weights of multilayer perceptron (MLP) modules, which are often identified as the main repositories of […]
Community Detection on Model Explanation Graphs for Explainable AI
arXiv:2510.27655v1 Announce Type: cross Abstract: Feature-attribution methods (e.g., SHAP, LIME) explain individual predictions but often miss higher-order structure: sets of features that act in concert. We propose Modules of Influence (MoI), a framework that (i) constructs a model explanation graph from per-instance attributions, (ii) applies community detection to find feature modules that jointly affect predictions, […]
Ferrohydrodynamic Microfluidics for Bioparticle Separation and Single-Cell Phenotyping: Principles, Applications, and Emerging Directions
arXiv:2510.26950v1 Announce Type: cross Abstract: Ferrohydrodynamic microfluidics relies on magnetic field gradients to manipulate diamagnetic particles in ferrofluid-filled microenvironments. It has emerged as a promising tool for label-free manipulation of bioparticles, including their separation and phenotyping. This perspective reviews recent progress in the development and applications of ferrofluid-based microfluidic platforms for multiscale bioparticle separation, ranging […]
e1: Learning Adaptive Control of Reasoning Effort
arXiv:2510.27042v1 Announce Type: new Abstract: Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value output quality versus latency and cost. To leverage this tradeoff effectively, users need fine-grained […]
Overview of the MEDIQA-OE 2025 Shared Task on Medical Order Extraction from Doctor-Patient Consultations
arXiv:2510.26974v1 Announce Type: cross Abstract: Clinical documentation increasingly uses automatic speech recognition and summarization, yet converting conversations into actionable medical orders for Electronic Health Records remains unexplored. A solution to this problem can significantly reduce the documentation burden of clinicians and directly impact downstream patient care. We introduce the MEDIQA-OE 2025 shared task, the first […]
HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search
arXiv:2507.02652v2 Announce Type: replace Abstract: Complex information needs in real-world search scenarios demand deep reasoning and knowledge synthesis across diverse sources, which traditional retrieval-augmented generation (RAG) pipelines struggle to address effectively. Current reasoning-based approaches suffer from a fundamental limitation: they use a single model to handle both high-level planning and detailed execution, leading to inefficient […]
A Framework for Fair Evaluation of Variance-Aware Bandit Algorithms
arXiv:2510.27001v1 Announce Type: cross Abstract: Multi-armed bandit (MAB) problems serve as a fundamental building block for more complex reinforcement learning algorithms. However, evaluating and comparing MAB algorithms remains challenging due to the lack of standardized conditions and replicability. This is particularly problematic for variance-aware extensions of classical methods like UCB, whose performance can heavily depend […]
Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement
arXiv:2510.27051v1 Announce Type: new Abstract: Enterprise AI agents must continuously adapt to maintain accuracy, reduce latency, and remain aligned with user needs. We present a practical implementation of a data flywheel in NVInfo AI, NVIDIA’s Mixture-of-Experts (MoE) Knowledge Assistant serving over 30,000 employees. By operationalizing a MAPE-driven data flywheel, we built a closed-loop system that […]
Elastic Architecture Search for Efficient Language Models
arXiv:2510.27037v1 Announce Type: cross Abstract: As large pre-trained language models become increasingly critical to natural language understanding (NLU) tasks, their substantial computational and memory requirements have raised significant economic and environmental concerns. Addressing these challenges, this paper introduces the Elastic Language Model (ELM), a novel neural architecture search (NAS) method optimized for compact language models. […]
Validation of contact mechanics models for Atomic Force Microscopy via Finite Elements Analysis and nanoindentation experiments
arXiv:2406.17157v4 Announce Type: replace-cross Abstract: In this work, we have validated the application of Hertzian contact mechanics models and corrections for the analysis of force vs indentation curves, acquired using spherical indenters on linearly elastic samples, by means of finite elements simulations and AFM nanomechanical measurements of polyacrylamide gels possessing a thickness gradient. We have […]