AI News

MLPerf Automotive (arxiv.org)

The kernel of graph indices for vector search (arxiv.org)

AIR: Analytic Imbalance Rectifier for Continual Learning (arxiv.org)

Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors (arxiv.org)

Self-Play Pretraining with Zero Data (arxiv.org)

Residual Correlation as a Diagnostic for Joint-Uncertainty Gains from GP Coregionalisation (arxiv.org)

Spatio-temporally complementary feature propagation on graphs for longitudinal AADT estimation (arxiv.org)

Classifier-Dependent Benefits of Pseudo-Labeling for Semi-Supervised Android Malware Attribution (arxiv.org)

NNV3: Expanding Neural Network Verification to New Architectures and Domains (arxiv.org)

Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models (arxiv.org)

How does Adversarial Influence Scale in Multi-Agent Systems? (arxiv.org)

Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark (arxiv.org)

Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems (arxiv.org)

Certified Predictive Value-of-Advice Gating for Cost-Aware Language-Model Guidance in Reinforcement Learning (arxiv.org)

Common Covariance Geometry and Certification for Brownian Kernel Ladders (arxiv.org)

Sample-Weighted End-to-End Trace-Norm Geometry for Multitask Learning (arxiv.org)

CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning (arxiv.org)

Spectral-Guided Diffusion: Accelerating Inference via Static Spectral Layer Scheduling (arxiv.org)

AgentKernel: The Trust-Native Agentic Operating System (arxiv.org)

Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search (arxiv.org)

TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification (arxiv.org)

UNWIND: Any-Length Facial Video for Stress Detection without Temporal Windowing (arxiv.org)

When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI (arxiv.org)

Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference (arxiv.org)

BLADE: Distilled LLM Regularization for Calibrated Knowledge Graph Completion (arxiv.org)

Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think (arxiv.org)

Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored Utility (arxiv.org)

Diverse Geometries, Frozen Weights: Robust Heterogeneous Treatment-Effect Estimation via Causal Expert Ensembles (arxiv.org)

A Contraction Framework for Stochastic Operators with Bootstrapping: Application to TD Learning (arxiv.org)

Generalized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse (arxiv.org)

Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models (arxiv.org)

From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation (arxiv.org)

SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification (arxiv.org)

FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates (arxiv.org)

Three Ways Classical Test Theory Misleads for LLM Judges (arxiv.org)

An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension (arxiv.org)

Bandit Multiclass PAC Learning: Corrected Lower Bounds, Exact Families, and a Confidence Direct-Sum Phenomenon (arxiv.org)

Predicting Symptoms of Amotivation and Anhedonia among University Students with a Novel Oversampling Method (arxiv.org)

WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement (arxiv.org)

Not All Synthetic Data Are Equal: Expert-Committee Audit Screening for Imbalanced Crash-Injury-Severity Prediction in Automated Driving Systems (arxiv.org)

Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context (arxiv.org)

GBFRVFL: Granular-Ball Computing-Based Fuzzy Random Vector Functional Link Network (arxiv.org)

A Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes (arxiv.org)

Limited Structural Reliability in Public Educational Prediction Benchmarks: A Four-Dimension Audit of Seven Datasets (arxiv.org)

Active Client Selection in Federated Trajectory Prediction with Uncertainty-Awareness and Heterogeneous Complexity (arxiv.org)

A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data (arxiv.org)

Investigating White Blood Cells as a Source of False-Positive Malaria Parasite Detection in African Blood-Smear Images (arxiv.org)

Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes (arxiv.org)

Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage (arxiv.org)

Does a model's stated reason for rejecting a candidate do any work? (arxiv.org)