AI News

K2-V2: A 360-Open, Reasoning-Enhanced LLM (arxiv.org)

Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct (arxiv.org)

Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems (arxiv.org)

MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs (arxiv.org)

PRIVET: PRoximIty leakage detection Via Extreme value Theory (arxiv.org)

CORDS: Continuous Representations of Discrete Structures (arxiv.org)

SteganoBackdoor: Evading Data-Poisoning Defenses via Steganographic Backdoors (arxiv.org)

CASE: Contrastive Activation for Class-Sensitive Explanations (arxiv.org)

Gradient-Stable Attention Heads Signal LLM Correctness (arxiv.org)

Adaptive Uncertainty-Aware Modeling and Stochastic Radial Basis Function Predictive Control for Personalized Fluid Resuscitation (arxiv.org)

RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding (arxiv.org)

Chronosphere: Space-Time Tessellation of Local Climate Experts (arxiv.org)

End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery (arxiv.org)

Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA (arxiv.org)

World Modeling in Transformers (arxiv.org)

Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation (arxiv.org)

Configurable Multi-Stage Vision Pipeline for Crop Disease and Pest Diagnosis (arxiv.org)

A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks (arxiv.org)

Detection is solved, delineation is not: what governs tooth segmentation on panoramic radiographs (arxiv.org)

CaLR: Causal Latent Revision for Robust Diffusion Reasoning (arxiv.org)

Scaling Discovery through Test-Time Communication (arxiv.org)

Multi-Domain Clustering via Measure Quantization (arxiv.org)

TALON: A Temporally Aware Longitudinal Framework for Radiology Report Generation (arxiv.org)

Beyond WER: Entity and Disfluency Recall in Accented Conversational ASR (arxiv.org)

Single-Loop Stochastic Projected Damped Extragradient Methods for Stochastic Nonconvex--(Strongly) Concave Minimax Optimization (arxiv.org)

Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw (arxiv.org)

$\lambda$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource (arxiv.org)

Triply-Scalable Equivariant Gaussian Process Modeling (arxiv.org)

Recursive Language Models Generalize Out of Domain (arxiv.org)

LoRA Enhanced Contrastive Learning with SAS Vision Transformers (arxiv.org)

Diagonalized Attention for Individualized Regression: Latent-Row Localization and Prediction (arxiv.org)

Sparse Identification for Automatic Large-Scale Screening: A Constraint-Aware Framework with Ultra Fast Decoding Algorithm (arxiv.org)

Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing (arxiv.org)

Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models (arxiv.org)

TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers (arxiv.org)

Periodic Neural Mapping for Unsteady Rotor-Blade Pressure and Aeroelastic Load Prediction (arxiv.org)

Near-Optimal Acceleration for Smooth $\ell_p$ / $\ell_q$ Nondual Convex First-Order Oracle Optimization (arxiv.org)

Do Quantum Models Scale Like LLMs? (arxiv.org)

REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement (arxiv.org)

ASGARD: Action-Space Guard for UAV Resilience via Reinforcement Learning (arxiv.org)

Bayesian classification of astronomical spectra with class uncertainties (arxiv.org)

Complete Neural Electronic Initialization Accelerates Materials DFT (arxiv.org)

PhysioBench: A Unified Benchmark for Physiological Signal Question Answering (arxiv.org)

Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks (arxiv.org)

Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening (arxiv.org)

Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake (arxiv.org)

Signal-Centric Remote Sensing via Alternative Preprocessing and Acoustic Processing for ML-Driven Applications (arxiv.org)

Neural composite likelihood estimation: simulation based inference for time series (arxiv.org)

EnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the Enterprise (arxiv.org)

dSTAR: Straggler Tolerant and Byzantine Resilient Distributed SGD (arxiv.org)