AI News

$t_0$: A Time-Series Foundation Model for Forecasting with Context (arxiv.org)

Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction (arxiv.org)

Overlay\_dx - Automating forecasting evaluation (arxiv.org)

Taking a Second Look: Correcting Sea Ice Forecasts with Sparse Observations (arxiv.org)

GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting (arxiv.org)

Augmented Hypothesis Testing with Persona-Based LLM Simulations (arxiv.org)

iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs (arxiv.org)

Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement (arxiv.org)

Muon Can Outperform Dedicated Continual Learning Methods (arxiv.org)

A Federated Artificial Intelligence Framework for Optimizing Pancreatic Cancer Treatment - Strategy Update (arxiv.org)

Machine Learning for Invisible Dark Boson Searches at the Electron-Ion Collider (arxiv.org)

Enhancing Transformer Representations of Symbolic ODE Expressions (arxiv.org)

Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data (arxiv.org)

Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention (arxiv.org)

G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation (arxiv.org)

When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting (arxiv.org)

Learning Prognostic Variables for AI Convective Parameterizations via Symbolic Distillation (arxiv.org)

Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization (arxiv.org)

1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation (arxiv.org)

Learning Physics from an Imperfect Ancestor (arxiv.org)

Rare Event Estimation via Iterative Unalignment (arxiv.org)

Artificial Structure Function Search: Preserving Artificial Functional Connectivity for Structured Pruning (arxiv.org)

Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systems (arxiv.org)

Climate Variability Modulates the Impact of Price Spikes on Food Insecurity (arxiv.org)

NAVIR: Neuromorphic Audio-Visual Speech Recognition for Robust Human-Robot Interaction on Edge Hardware (arxiv.org)

Machine Learning-Based Prediction of Childhood Stunting in Bangladesh: Fairness and Temporal Robustness Assessment (arxiv.org)

Credit Access is Associated with Improved Food Security in the Horn of Africa (arxiv.org)

Information-Time Proximal Policy Optimization (arxiv.org)

Prescriptive SVD-Inspired Attention via Spectral Energy Retention (arxiv.org)

Counting and Covering in Nearest-Neighbour Representations of Boolean Functions (arxiv.org)

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving (arxiv.org)

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

Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces (arxiv.org)

Leakage-Safe Empirical Benchmarking of EEG-Based Machine Learning Pipelines for Dementia Classification (arxiv.org)

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

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

Explainable Predictive Condition-based Maintenance of Naval-Propulsion Systems using Fuzzy Logic (arxiv.org)

Summarize, Judge, Refine: Decoupled Content Understanding and Policy Learning for Multimodal Content Moderation (arxiv.org)

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

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

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

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

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

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

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

Beyond the Raw Waveform: Fusing Visual Representations of EDA for Stress Detection (arxiv.org)

Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models (arxiv.org)

Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents (arxiv.org)

Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents (arxiv.org)

When Does Test-Time Physical Diagnosis Pay? A Frozen Policy Buys Evidence It Never Reads (arxiv.org)