AI News

AI Emulation of Stochastic Sudden Stratospheric Warming with Interpretable Latent Structure (arxiv.org)

Sequential Capacity of Quantum Processes with Finite Memory (arxiv.org)

Weather-Aware Domain Adaptation for Street-View Weather Recognition (arxiv.org)

Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities (arxiv.org)

Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage (arxiv.org)

Training-Free Diffusion Planning with Analytical Local Scores (arxiv.org)

A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders (arxiv.org)

Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models (arxiv.org)

LAST: Looped Audio Spectrogram Transformer (arxiv.org)

A Structured State Space Sequence Model for Multi-Class Classification of Malware (arxiv.org)

TRACE: Tackling Real-World Resource Assignment Problems via Agentic Heuristic Design (arxiv.org)

Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment? (arxiv.org)

Optimal Stochastic Bilevel Optimization with First-Order Oracles (arxiv.org)

Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography (arxiv.org)

Code Owns the Simulation, Jev Owns the Evaluation (arxiv.org)

Generalized Engression Models (arxiv.org)

PhaseAT: Fourier Phase Adversarial Training for Medical Image Domain Generalization (arxiv.org)

On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D (arxiv.org)

Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift (arxiv.org)

Q-Learning for Reachability in MEC-Free MDPs (arxiv.org)

The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching (arxiv.org)

Designing for Interpretation Uncertainty: Architecture and Principles for Topological Learning Analytics Dashboards (arxiv.org)

Comparing a gradient boosting algorithm to the GOES FDC for wildfire detection (arxiv.org)

End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems (arxiv.org)

Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses (arxiv.org)

Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation (arxiv.org)

Lower Bounds for Stochastic First-Order Algorithms with Variance Reduction in Nonconvex--Concave Minimax Optimization (arxiv.org)

Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators (arxiv.org)

Transferable Graph Metanetworks (arxiv.org)

Benchmarking Prompt Optimization of Large Language Models With Chess (arxiv.org)

Interpreting Reasoning of Large Language Models via Partial Information Decomposition (arxiv.org)

On the Relationship between Model Quantization and Model Inversion Attacks (arxiv.org)

Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation (arxiv.org)

LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation (arxiv.org)

ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair (arxiv.org)

Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing (arxiv.org)

CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters (arxiv.org)

When Do Intrinsic Rewards Lead to Exploration? (arxiv.org)

Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning (arxiv.org)

DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies (arxiv.org)

Beyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents (arxiv.org)

Multi-Resolution Feature Fusion U-Net for Magnetic Resonance Imaging Segmentation (arxiv.org)

System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer (arxiv.org)

Compositional Embedding Architecture for Physical Field Prediction in Componentized Aerospace Systems (arxiv.org)

Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole (arxiv.org)

Learning to Price Electricity for Optimal Demand Response (arxiv.org)

When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora (arxiv.org)

Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor (arxiv.org)

Symmetry Discovery in Quantum Learning: Observable-Level and Task-Level Inference from Finite Measurements (arxiv.org)

Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers (arxiv.org)