AI News

⚡ 12 minutes ago
1
1
Data augmented bootstrap: Unifying confidence interval construction by approximate invariance (arxiv.org)
2
1
Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin (arxiv.org)
3
1
Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs (arxiv.org)
4
1
Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory (arxiv.org)
5
1
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR (arxiv.org)
6
1
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability (arxiv.org)
7
1
CP-factorization for high dimensional tensor time series and double projection iterations (arxiv.org)
8
1
Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement (arxiv.org)
9
1
Nonparametric undirected graphical model selection using diffusion models (arxiv.org)
10
1
When Are Neural Interaction Discoveries Real? Identifiability, Recoverability, and a Pre-Fit Diagnostic (arxiv.org)
11
1
The Spectral Dynamics and Noise Geometry of Muon (arxiv.org)
12
1
A Switching Beamformer for Highly Non-Stationary Environments (arxiv.org)
13
1
How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs (arxiv.org)
14
1
Assessing model calibration with boosting trees (arxiv.org)
15
1
Inference for High-Dimensional Sparse Spectral Precision Matrices (arxiv.org)
16
1
Partially Performative Prediction (arxiv.org)
17
1
Instrumented data for causal scientific machine learning (arxiv.org)
18
1
Large-scale empirical tuning and comparison of default optimizers for variational inference (arxiv.org)
19
1
A Framework for Evaluating and Benchmarking Concept Drift Detection Methods (arxiv.org)
20
1
Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head (arxiv.org)
21
1
MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport (arxiv.org)
22
1
Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections (arxiv.org)
23
1
Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees (arxiv.org)
24
1
Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls (arxiv.org)
25
1
Generalization in Nonlinear Least Squares via Learned Feature Geometry (arxiv.org)
26
1
Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation (arxiv.org)
27
1
Improving the sharpness in neural network-based parametric post-processing of ensemble forecasts (arxiv.org)
28
1
Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs (arxiv.org)
29
1
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry (arxiv.org)
30
1
Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models (arxiv.org)
31
1
MEC-Cox: Machine-Learning-Assisted Generalized Entropy Calibration for ATT Marginal Hazard-Ratio Estimation (arxiv.org)
32
1
Vector Space of Cycles (arxiv.org)
33
1
INFUSER: Influence-Guided Self-Evolution Improves Reasoning (arxiv.org)
34
1
Beyond Additivity: Causal Discovery in Location-Scale Noise Models with Hidden Variables (arxiv.org)
35
1
Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance (arxiv.org)
36
1
(Auto)formalization is supposed to be easy: Trellis process semantics for spelling out rigorous proofs (arxiv.org)
37
1
Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search (arxiv.org)
38
1
PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning (arxiv.org)
39
1
Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning (arxiv.org)
40
1
Trajectory Geometry of Transformer Representations Across Layers (arxiv.org)
41
1
Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directions (arxiv.org)
42
1
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)
43
1
Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing (arxiv.org)
44
1
Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents (arxiv.org)
45
1
The AI Epistemic Deference Index: A Continuous Measure of Sycophancy (arxiv.org)
46
1
Emergent alignment and the projectability of ethical personas (arxiv.org)
47
1
Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation (arxiv.org)
48
1
ERBench: A Benchmark and Testsuite for Equation Discovery Algorithms (arxiv.org)
49
1
Orange Lab: Lowering Barriers to Data Mining through Embedded Interactive Workflows (arxiv.org)
50
1
The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection (arxiv.org)