AI News

Learning Heterogeneous Preferences (arxiv.org)

A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning (arxiv.org)

FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment (arxiv.org)

SAGE: Governed Artifact Generation from Enterprise Guidelines (arxiv.org)

Imitation Learning for Autonomous Driving in CARLA (arxiv.org)

A Systematic Evaluation of the COTQ Provincial Land Cover Product: Structural Consistency, Spectral Separability, and Relative Positioning Against ESA, ESRI, and Google Products (arxiv.org)

NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation (arxiv.org)

GVD: Governed Versioning and Deduplication for Document Repositories (arxiv.org)

What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization (arxiv.org)

Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees (arxiv.org)

One Color Preprocessing Improves DSATUR (arxiv.org)

Rank and computation of the pathlifting Jacobian of a DAG ReLU network (arxiv.org)

Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows (arxiv.org)

Generalized DCCQ: From Binary Quotients to Multinomial Simplex Geometry and Critical-Strip Coordinates (arxiv.org)

R\'enyi Tracking Bounds for Langevin Dynamics with Moving Targets (arxiv.org)

Functional BART with Shape Priors: A Bayesian Tree Approach to Constrained Functional Regression (arxiv.org)

Breaking the $T^{2/3}$ Barrier for Sequential Calibration (arxiv.org)

Bayesian Quadrature (arxiv.org)

Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging (arxiv.org)

Learning to Program Adaptive Non-Local Observables for Machine Learning (arxiv.org)

EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents (arxiv.org)

CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video (arxiv.org)

GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents (arxiv.org)

Finite-Sample Unbiased Variance of MMD under Unbalanced Sampling: Exact Estimation and Quasi-Linear Computation (arxiv.org)

Spectral gap of Metropolis-within-Gibbs under log-concavity (arxiv.org)

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models (arxiv.org)

Physics-Informed Sylvester Normalizing Flows for Bayesian Inference in Magnetic Resonance Spectroscopy (arxiv.org)

Stable Filters for Generative Modeling of Graph Signals (arxiv.org)

When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arxiv.org)

Correcting Boundary Bias and Observation Independence in Bayesian Experimental Design (arxiv.org)

Revisiting Distributed Sign-Based Variance Reduction (arxiv.org)

How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction (arxiv.org)

Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders (arxiv.org)

Spatially Adaptive Noise Injection (arxiv.org)

Gradient Descent with Stochastic Subspaces via Persistence of Memory (arxiv.org)

Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts (arxiv.org)

Beyond Quadratic Loss: The Stability Phase Diagram of Adam (arxiv.org)

Matching Multi-Loop Complexities with a Single Loop: Optimal Optimization Stationarity and Best-Known Game Stationarity in Nonconvex--Concave Minimax Optimization (arxiv.org)

On the Identifiability of Mixed Ordinal and Exponential Family Causal DAGs under Linear Parametric Models (arxiv.org)

Symmetry without a manifold: intrinsic dimension on orbits (arxiv.org)

TabPFN-3.5: Technical Report (arxiv.org)

Approximating Measures on Function Spaces: Transport and Truncation (arxiv.org)

Random tilts to find stationary points in stochastic convex optimization (arxiv.org)

Efficient Robust Learning at the Information-Theoretic Limit (arxiv.org)

Fenchel-Young Duality Gaps: Certified Early Stopping for Regularized Inverse Problems (arxiv.org)

Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds (arxiv.org)

A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings (arxiv.org)

Fast Learning Rates for Physics-Informed Kernel Methods (arxiv.org)

Bracketing Uncertainty in Clustering Under the Manifold Hypothesis (arxiv.org)

Sharp margin-based generalization bounds for realizable SVM (arxiv.org)