AI News

Data augmented bootstrap: Unifying confidence interval construction by approximate invariance (arxiv.org)

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin (arxiv.org)

Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs (arxiv.org)

Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory (arxiv.org)

sGPO: Trading Inference FLOPs for Training Efficiency in RLVR (arxiv.org)

Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability (arxiv.org)

CP-factorization for high dimensional tensor time series and double projection iterations (arxiv.org)

Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement (arxiv.org)

Nonparametric undirected graphical model selection using diffusion models (arxiv.org)

When Are Neural Interaction Discoveries Real? Identifiability, Recoverability, and a Pre-Fit Diagnostic (arxiv.org)

The Spectral Dynamics and Noise Geometry of Muon (arxiv.org)

A Switching Beamformer for Highly Non-Stationary Environments (arxiv.org)

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs (arxiv.org)

Assessing model calibration with boosting trees (arxiv.org)

Inference for High-Dimensional Sparse Spectral Precision Matrices (arxiv.org)

Partially Performative Prediction (arxiv.org)

Instrumented data for causal scientific machine learning (arxiv.org)

Large-scale empirical tuning and comparison of default optimizers for variational inference (arxiv.org)

A Framework for Evaluating and Benchmarking Concept Drift Detection Methods (arxiv.org)

Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head (arxiv.org)

MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport (arxiv.org)

Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections (arxiv.org)

Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees (arxiv.org)

Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls (arxiv.org)

Generalization in Nonlinear Least Squares via Learned Feature Geometry (arxiv.org)

Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation (arxiv.org)

Improving the sharpness in neural network-based parametric post-processing of ensemble forecasts (arxiv.org)

Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs (arxiv.org)

LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry (arxiv.org)

Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models (arxiv.org)

MEC-Cox: Machine-Learning-Assisted Generalized Entropy Calibration for ATT Marginal Hazard-Ratio Estimation (arxiv.org)

Vector Space of Cycles (arxiv.org)

INFUSER: Influence-Guided Self-Evolution Improves Reasoning (arxiv.org)

Beyond Additivity: Causal Discovery in Location-Scale Noise Models with Hidden Variables (arxiv.org)

Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance (arxiv.org)

(Auto)formalization is supposed to be easy: Trellis process semantics for spelling out rigorous proofs (arxiv.org)

Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search (arxiv.org)

PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning (arxiv.org)

Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning (arxiv.org)

Trajectory Geometry of Transformer Representations Across Layers (arxiv.org)

Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directions (arxiv.org)

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory (arxiv.org)

Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing (arxiv.org)

Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents (arxiv.org)

The AI Epistemic Deference Index: A Continuous Measure of Sycophancy (arxiv.org)

Emergent alignment and the projectability of ethical personas (arxiv.org)

Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation (arxiv.org)

ERBench: A Benchmark and Testsuite for Equation Discovery Algorithms (arxiv.org)

Orange Lab: Lowering Barriers to Data Mining through Embedded Interactive Workflows (arxiv.org)

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection (arxiv.org)