AI News

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

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

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

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

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

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

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

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

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

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

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

Learning the Cost of Reliable Inference (arxiv.org)

The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models (arxiv.org)

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

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

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

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

Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving (arxiv.org)

Untangling the Geometry and Speed for RF Sensing Spectrograms (arxiv.org)

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

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

Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies (arxiv.org)

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

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

LexLattice: Multilingual Extractive Summarization via Neural Cellular Automata on Document Hierarchies (arxiv.org)

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

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

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

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

Resource-Adaptive Stochastic Gradient Descent for Online Linear Programming without Re-solving (arxiv.org)

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

CVaR anchor regression protects against rare shifts (arxiv.org)

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

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

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

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

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

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

When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment (arxiv.org)

Memory Attention (arxiv.org)

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

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

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

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

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

Constraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems (arxiv.org)

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

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