AI News

Reliable Fusion of Conflicting Experts (arxiv.org)

NPBoost: Neural Processes with Gradient-Boosted Fixed Effects (arxiv.org)

Outlier Detection for Multi-Network Data (arxiv.org)

Gaussian-process surrogate indicators for residual-based adaptive GMsFEM (arxiv.org)

Additive Nonparametric Regression with Spatial and Network Objects (arxiv.org)

Rolling Conformal Prediction in Sequential Model Training (arxiv.org)

WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps (arxiv.org)

The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems (arxiv.org)

Change detection with conformal martingales: new optimal constructions, and suboptimality of existing methods (arxiv.org)

Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following (arxiv.org)

Robustness of Diffusion Models under Distribution Shift (arxiv.org)

The Type-II Error of Test Supermartingales: e-Power versus the Chernoff-Stein Exponent (arxiv.org)

Type-II Error Bounds for Test Supermartingales from Lower-Tail Hypotheses (arxiv.org)

Financial Tail Risk Beyond Lipschitz Continuity via Semi-Discrete Optimal Transport (arxiv.org)

Optimal State-Space Order for Spectral Gaps of Sliding-Window Occupation Counts (arxiv.org)

Dirichlet Process Mixtures of Trees with Gaussian Process Splits: A Bayesian Nonparametric Framework with Posterior Contraction Rate (arxiv.org)

Functional Causal Discovery via Conditional Covariance Ordering (arxiv.org)

Fourth-Moment Strong Universality for Finite-Type Transpose-Correlated Random Matrices (arxiv.org)

Rank-One Signal Recovery in Sparse Wishart Noise (arxiv.org)

Random Polytope Descriptors (arxiv.org)

Localized Diffusion Models (arxiv.org)

Role of scrambling and noise in temporal information processing with quantum systems (arxiv.org)

BOCO: Bayesian Online Contextual Optimization for Decision-Focused Online Learning (arxiv.org)

Advances in Diffusion-Based Generative Compression (arxiv.org)

Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse (arxiv.org)

Context-Continuous Preference Learning for Exoskeleton Personalization (arxiv.org)

NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution (arxiv.org)

What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus (arxiv.org)

Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model (arxiv.org)

Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts (arxiv.org)

LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels (arxiv.org)

A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction (arxiv.org)

COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation (arxiv.org)

QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs (arxiv.org)

Marginally Correct Tool Caches Can Reverse Group-Normalized Policy Updates (arxiv.org)

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation (arxiv.org)

CORE-STACK+: Meta-Learning for Deep Stacked Generalization (arxiv.org)

On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning (arxiv.org)

Provably Complete Generalized Planning with LLMs (arxiv.org)

Are Stated Reasoning Steps Causally Load-Bearing? (arxiv.org)

Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity (arxiv.org)

TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents (arxiv.org)

Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations (arxiv.org)

Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment (arxiv.org)

When Post-Processing Fairness Constraints Help and When They Harm: Evidence from Eight Cross-Domain Evaluations (arxiv.org)

Transfer Learning with Conformalized Quantile Regression for Solar PV Forecasting Under Load-Shedding-Driven Data Scarcity (arxiv.org)

CRISP: Scalable Importance-Stratified Coresets for Imbalanced Tabular Learning (arxiv.org)

TinyUDE: Solver-Free Universal Differential Equations on Microcontrollers via Lie-Taylor Jet Matching (arxiv.org)

Resource-Efficient Distributed Recursive Gaussian Processes (arxiv.org)

GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals (arxiv.org)