AI News

Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters (arxiv.org)

fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series (arxiv.org)

The Last Human Gate: Forward Deployed Engineering for Governance Automation (arxiv.org)

Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses (arxiv.org)

Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination (arxiv.org)

An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer (arxiv.org)

Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach (arxiv.org)

OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds (arxiv.org)

Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies (arxiv.org)

Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models (arxiv.org)

LabFactory: Building and Evaluating Executable AI Labs (arxiv.org)

Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities (arxiv.org)

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures (arxiv.org)

SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories (arxiv.org)

Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy (arxiv.org)

Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets (arxiv.org)

Clinical Knowledge Graphs for Chest X-Ray Device Reasoning (arxiv.org)

Safe Skill Retirement for Physical Agents (arxiv.org)

Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning (arxiv.org)

Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling (arxiv.org)

The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning (arxiv.org)

Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes (arxiv.org)

ERRAND: Budgeted Maintenance of Agent Memory (arxiv.org)

Monitoring Urban Traffic Dynamics at Fine Spatiotemporal Resolution Using Distributed Acoustic Sensing and Deep Learning (arxiv.org)

Stream Recursion Model (SRM) (arxiv.org)

When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection (arxiv.org)

LastOPD: Taming Collapse in Latent On-Policy Distillation (arxiv.org)

AI-based detection of worsening heart failure from low-resolution telemonitoring data (arxiv.org)

Cross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition (arxiv.org)

PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation (arxiv.org)

Sequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy (arxiv.org)

PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging (arxiv.org)

iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model (arxiv.org)

Ingest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora (arxiv.org)

Image Fidelity is Not Field Fidelity: Joint Thermodynamic Reconstruction and Error Localization in Neural Tomography (arxiv.org)

Response-state Learning for Transferable Vibrational Spectroscopic Characterization with Electron Prior (arxiv.org)

Spectral Graph Neural Networks with Hermite Polynomials: A Comprehensive Study (arxiv.org)

Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents (arxiv.org)

Downside-Controlled Online Forecast Combination under Delayed and Revised Outcomes (arxiv.org)

Learning from Mixed-Quality Deployment Experience for Robot Manipulation (arxiv.org)

Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN (arxiv.org)

Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces (arxiv.org)

BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization (arxiv.org)

Physics and Data Driven Transformer-Mamba Framework for Flow Field (arxiv.org)

To Think or Not to Think: Allocating Reasoning Where It Helps (arxiv.org)

Fair Like Us? Auditing LLM Alignment in Resource Allocation (arxiv.org)

A General Framework for Budgeted Threshold Incentives on Request (arxiv.org)

The Gold in Bias: Maturing the AI Design Process through Verification (arxiv.org)

C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks (arxiv.org)

Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER (arxiv.org)