AI News

Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection (arxiv.org)

Actionable Insights from Observational Data: The Case of Advanced Classes in K-12 Education (arxiv.org)

From Regional to Global: Transfer Learning for Atmospheric Transport Emulators (arxiv.org)

Adaptive Determinantal Client Scheduling in Federated Learning (arxiv.org)

PROSE: A Theory of Optimal Stopping with Perishable Evidence for Peer Selection in Intermittently Connected Decentralised Learning (arxiv.org)

VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking (arxiv.org)

GLR-MM: Graph-Based Global-Local Reconstruction for Robust Multimodal Chest X-ray and EHR Representation Learning under Missing Modalities (arxiv.org)

Collaborative Streaming Anomaly Detection with Interactive Explanations and Ensemble Consensus (arxiv.org)

Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs (arxiv.org)

GDN Tree-Scan: Served Tree Verification for Recurrent-Hybrid Language Models (arxiv.org)

Multivariate quantile regression via Kolmogorov-Arnold Networks (arxiv.org)

A discrete generative model of neuronal spiking activity on microelectrode arrays (arxiv.org)

Matched-Input Estimates Differ in Sign Across Architectures: Auditing EEG Foundation Models on Motor Imagery (arxiv.org)

The Neural Forcing for Three-Dimensional Incompressible Navier-Stokes finite time blowup (arxiv.org)

AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows (arxiv.org)

MGRD: Compact morphology-gated residual diffusion for variance-aware cross-domain neurite forecasting (arxiv.org)

Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets (arxiv.org)

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision (arxiv.org)

ZoAQ: Adaptive Zeroth-Order Querying via Query-Reuse Coupling (arxiv.org)

Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models (arxiv.org)

Graph Learning for Cross-Subject, Cross-Population EEG Emotion Decoding and Model-Derived Spatial-Spectral Neural Signatures (arxiv.org)

Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction (arxiv.org)

Evaluation Awareness Shifts from Format to Context with Model Scale (arxiv.org)

ST-Topo GAN: A Motor EEG-to-EMG Decoding Model Matched to Wrist Movement Complexity (arxiv.org)

Correlation-Aware Structured Pruning for Large Language Models (arxiv.org)

WiNeRF: Measurement Constrained Radiance Fields for Actionable Wireless Channel Modeling (arxiv.org)

Experimental Evaluation of a Low-Power Ultra-Wideband Receiver for Spectrum Sensing (arxiv.org)

DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detection (arxiv.org)

Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish (arxiv.org)

HFEMCNet: A Compact Hybrid Frequency Enriched Multi Channel Network for Automatic Modulation Classification (arxiv.org)

Attention-Enhanced Dual-Branch ConvNeXt-BiLSTM Network for Subject-Independent EEG Seizure Detection (arxiv.org)

When Does Learning Beat Heuristics? A Case Study in Kubernetes Scheduler Score Plugins (arxiv.org)

Using Composition Operators to Linearize LLM Semantic Transformations (arxiv.org)

ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning (arxiv.org)

Gradient-estimator design overcomes trainability barriers in neural-network-based variational optimization (arxiv.org)

Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients (arxiv.org)

A Hybrid Quantum Neural Network to Analyse Big Experimental Powder X-ray Diffraction Data (arxiv.org)

Forecasting Intrathecal Tracer Enhancement from Pre-Contrast Brain MRI: Direct Regression versus Flow Matching (arxiv.org)

Replication Without Persistence in Hosted LLMs: Measurement Sensitivity in Action-Time Belief Evaluation (arxiv.org)

AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation (arxiv.org)

A principled approach for energy-efficient training via phase-aware GPU frequency tuning (arxiv.org)

MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents (arxiv.org)

MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents (arxiv.org)

High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability (arxiv.org)

TTSE: A Two-Track Online Self-Evolution Framework (arxiv.org)

KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation (arxiv.org)

SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration (arxiv.org)

The Undetected Damage of Quantization on Retrieval and How to Fix It (arxiv.org)

Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse (arxiv.org)

Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime (arxiv.org)