AI News

Global tree forecasters collapse at the hierarchical aggregate: a five-panel failure characterization (arxiv.org)

Spread and Scale: What Determines Whether Test-Time Budget Allocation Pays (arxiv.org)

Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure (arxiv.org)

Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions (arxiv.org)

Quality over Quantity: Semi-Supervised Detection of Illicit Bitcoin Flows via Feature Engineering (arxiv.org)

When Accuracy Gaps Fail to Certify: Auditing Cross-Domain Recalibration of LLM Judges (arxiv.org)

Semantic Self-Distillation for Language Model Uncertainty (arxiv.org)

CS-WCP: Robust Conformal Sets for LLM-Judge Traffic Shifts with Uncertain Group Proportions (arxiv.org)

I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation (arxiv.org)

Linear RNN Scaling Laws: When Longer Sequences Beat More Sequences (arxiv.org)

Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices (arxiv.org)

From Sentiment Classification to Actionable and Responsible Feedback: A Scoping Review and Evidence Map of NLP in Student Evaluation of Teaching, 2015-2026 (arxiv.org)

Agentic Governance and Adversarial Verification for Policy-Constrained LLM Healthcare Appeal Generation (arxiv.org)

Reachable Global Optimization in AI Systems: How Global Is Global? (arxiv.org)

A hierarchy of faithfulness criteria for knowledge base completion (arxiv.org)

Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents (arxiv.org)

A Resilience Recovery Method for Complex Traffic Network Security Based on Trend Forecasting (arxiv.org)

SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference (arxiv.org)

Discovery of fully efficient fault indicators along a data-based diagnosis process (arxiv.org)

Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination (arxiv.org)

Enhancing Multiclass Malware Classification in Resource-Constrained Environments (arxiv.org)

The Recall Ceiling of LLM Recommendation Reranking (arxiv.org)

ScoutNeRV: Rapid Encoding of Grid-Based Video INRs via ScoutNet (arxiv.org)

Shutdown Sabotage Propensities in Multi-Agent Systems (arxiv.org)

Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery (arxiv.org)

Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets (arxiv.org)

Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces (arxiv.org)

Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints (arxiv.org)

Learning the Cost of Reliable Inference (arxiv.org)

An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice (arxiv.org)

StudentBench: AI and human tutoring yield equivalent GRE learning gains (arxiv.org)

G\"odel's and Scott's Variants of the Ontological Argument in Lean 4 (arxiv.org)

SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials (arxiv.org)

Tensor Decomposition of Transformer Key-Value Caches: Spectral Structure and Format Comparison (arxiv.org)

Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness (arxiv.org)

EMA: Elastic and Performance Transparent Memory Across GPUs (arxiv.org)

EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues (arxiv.org)

Does Graph Structure Earn Its Place in Microservice Root-Cause Analysis? A Controlled Study on RCAEval, and What the Benchmark Was Really Measuring (arxiv.org)

Learning Stiffness Dependent Fluid Structure Dynamics from Coarse Flow Representations (arxiv.org)

Bridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management (arxiv.org)

Validation and Simulation Catch Different Errors: Four Levels of Evaluation for LLM-Generated Circuits (arxiv.org)

Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation (arxiv.org)

Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning (arxiv.org)

Relative Discharge Stage (RDS) Classification: A Practical Indicator of Battery Discharge Progress (arxiv.org)

PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue (arxiv.org)

Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents (arxiv.org)

Shared Global KV with Layer-Specific Local History (arxiv.org)

SsgCaps: A controlled dataset for the evaluation of sound scene generation algorithms (arxiv.org)

FLINT: Fast Lightweight Inference for Traversability (arxiv.org)

Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection (arxiv.org)