AI News

Reverse Item Response Theory for Sparsity-Robust Ranking in Fragmented Cancer Drug-Response Matrices (arxiv.org)

Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning (arxiv.org)

How Far is Adam from Natural Gradient Descent? (arxiv.org)

FourierQK: Filter Shape, Admissibility and the Leakage-Coverage Law (arxiv.org)

Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System (arxiv.org)

Fast Polynomial Transcendentals for LLMs (arxiv.org)

SW-KAN: Kolmogorov-Arnold Networks with Stieltjes-Wigert q-Orthogonal Polynomials (arxiv.org)

"very likely" Means "uncertain"? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification (arxiv.org)

Nous: Learning and Certifying Memory Decisions Before Source Calibration (arxiv.org)

One Mastery Threshold Does Not Fit All Knowledge Tracing Models (arxiv.org)

Uncertainty-Aware Learning from Multi-Expert Interval Targets (arxiv.org)

The Hidden Costs of 99% Accuracy: A Trustworthiness Audit of the Telco Customer Churn Benchmark (arxiv.org)

Generalized Biomedicine Discovery (arxiv.org)

Classification Based on Association Rules Algorithm for Breast Cancer (arxiv.org)

Uncertainty-Aware RL-Controlled Adaptive 3D Mapping (arxiv.org)

Energy Time-Series Imputation with Differentially Private Diffusion Models via Clipping-Aware Objective Conditioning (arxiv.org)

Sharp Oracle-Regret Tradeoffs for Projection-Free Online Convex Optimization (arxiv.org)

Useful to Whom? Sample Value Is Defined Only Relative to the Learner (arxiv.org)

Constant-Memory Recall: Learned Associations in a Fixed Matrix State (arxiv.org)

How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds (arxiv.org)

Contingent Exposure Routing for Financial AI: Outage Risk and the Cost of Indivisible Decisions (arxiv.org)

The Null Is the Hard Part: Exact Tests for Memorization in Generative Models (arxiv.org)

Verification Pulses and the Cost of Escaping Wrong Consensus (arxiv.org)

Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces (arxiv.org)

Large Language Bayes Is Not Reparameterisation-Invariant (arxiv.org)

MOVE: Multimodal Open-world Verification and Expansion for Graph Learning (arxiv.org)

Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Models (arxiv.org)

Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics (arxiv.org)

Partial AUC Maximization from Positive-unlabeled Data (arxiv.org)

Bellman-Certified Rounding for Sparse Policy Deployment in MDPs (arxiv.org)

Beyond Diagonal State Space Models: Exact Non-Abelian Group Tracking, Solvability Barriers, and Geometric Physical Manifolds (arxiv.org)

The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning (arxiv.org)

Benchmarking System One decision models against trained classifiers and language models for automated decision gates (arxiv.org)

Deep Learning for Anomaly Detection in Railway Systems: A Structured Survey (arxiv.org)

Manifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment (arxiv.org)

MoRA: MoE Pruning via Router Bias Learning and Expert Approximation (arxiv.org)

M$^2$Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting (arxiv.org)

When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls (arxiv.org)

A First Glance at Jev for Network Traffic Classification: Accuracy, Processing Time, and Cost (arxiv.org)

STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting (arxiv.org)

Fusion techniques of time frequency-based images to predict the outcome of rTMS depression therapy (arxiv.org)

OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One (arxiv.org)

EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses (arxiv.org)

FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training (arxiv.org)

T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning (arxiv.org)

MatrixReward: Reward from Rubric Matrix for Open-Ended Generation (arxiv.org)

Interpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps (arxiv.org)

Forking: Sudden Overfitting Under Replay (arxiv.org)

Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo (arxiv.org)

Format-Aware Fusion for Fast FP4 Pretraining (arxiv.org)