AI News

⚡ 15 minutes ago
1
1
Embodiment-Induced Coordination Regimes in Tabular Multi-Agent Q-Learning (arxiv.org)
2
1
Breaking the Data Barrier in Learning Symbolic Computation: A Case Study on Variable Ordering Suggestion for Cylindrical Algebraic Decomposition (arxiv.org)
3
1
Cross-reality location privacy protection in 6G-enabled vehicular metaverses: an LLM-enhanced hybrid generative diffusion model-based approach (arxiv.org)
4
1
Atlas 2 -- Foundation models for clinical deployment (arxiv.org)
5
1
Security Without Detection: Economic Denial as a Primitive for Edge and IoT Defense (arxiv.org)
6
1
Fast State-Augmented Learning for Wireless Resource Allocation with Dual Variable Regression (arxiv.org)
7
1
Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection (arxiv.org)
8
1
Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits (arxiv.org)
9
1
Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers (arxiv.org)
10
1
From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning (arxiv.org)
11
1
On the Convergence of Stochastic Low-Rank Adaptation (arxiv.org)
12
1
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning (arxiv.org)
13
1
Trajectory-Regularized Stochastic Optimal Control via KL Divergence (arxiv.org)
14
1
Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge (arxiv.org)
15
1
LatentFlow: Visual Analytics for Latent Space Analysis in Molecular Graph Neural Networks (arxiv.org)
16
1
RIS-Kernel: A Model-Agnostic Architecture for Long-Context LLM Inference via Sparse Attention (arxiv.org)
17
1
MissHyper: Restoring Clinical Synchronicity in Missingness-Guided Hypergraph Forecasting (arxiv.org)
18
1
Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement (arxiv.org)
19
1
Variance-Reduced Q-Learning over Static and Time-Varying Networks (arxiv.org)
20
1
LeAct: Learning to Reason from Expert Actions (arxiv.org)
21
1
Searching the Space of Feed-Forward Neural-Network Weight-Update Rules with Fixed Depth Symbolic Regression (arxiv.org)
22
1
A Graph-Based Control Interface for Traffic Signals on Heterogeneous Road Networks (arxiv.org)
23
1
Data eccentricity, asymptotics of Gaussian RBF reproducing kernel Hilbert space, and kernel PCA (arxiv.org)
24
1
Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness (arxiv.org)
25
1
Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection (arxiv.org)
26
1
MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion (arxiv.org)
27
1
On the Depth Scalability of Logic Gate Networks (arxiv.org)
28
1
Cloud-Native Evaluation-as-a-Service: A Microservices Architecture for Scalable AI Monitoring with Conformal Guarantees (arxiv.org)
29
1
Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models (arxiv.org)
30
1
Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions (arxiv.org)
31
1
Automatic Stability and Recovery for Neural Network Training (arxiv.org)
32
1
Decentralized Multi-Agent Swarms for Autonomous Grid Security in Industrial IoT: A Consensus-based Approach (arxiv.org)
33
1
gp2Scale: A Class of Compactly Supported Non-Stationary Kernels and Distributed Computing for Exact Gaussian Processes on 10 Million Data Points (arxiv.org)
34
1
CorVS+: Correspondence-Driven Association of Video Trajectories and Sensors for Identity-Aware Person Localization in Warehouses (arxiv.org)
35
1
Numerical Fragility in Transformers: A Layer-wise Theory for Risk Estimation and Selective Stabilization (arxiv.org)
36
1
Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning (arxiv.org)
37
1
Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models (arxiv.org)
38
1
Spatially-Enhanced Temporal Fusion Transformer: Interpretable Multi-Output Prediction for Parametric Dynamical Systems with Time-Varying Inputs (arxiv.org)
39
1
Carpe Diem: Critical Learning Period-Aware Contract-Based Incentives for Federated Learning (arxiv.org)
40
1
PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest (arxiv.org)
41
1
Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support (arxiv.org)
42
1
Singular value soft-thresholding via the polar decomposition (arxiv.org)
43
1
TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI (arxiv.org)
44
1
Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability (arxiv.org)
45
1
Reflector: Arrangement-Aware Harmonic Retrieval for Sample-Based Composition (arxiv.org)
46
1
Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models (arxiv.org)
47
1
HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding (arxiv.org)
48
1
Agentic Root Cause Analysis through Evidence-Grounded Reasoning (arxiv.org)
49
1
Deep Convolutional Large-Margin $\ell_p$-SVDD for Visual Anomaly Detection (arxiv.org)
50
1
Bowel Obstruction Detection and Localization on Abdominal CT with Deep Learning (arxiv.org)