AI News

CVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language Models (arxiv.org)

Benchmarking Candidate Coverage in Typed Decision Models (arxiv.org)

DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents (arxiv.org)

Joint Movement and Compression Ratio Design for Mobile Embodied AI Networks (MEAN) (arxiv.org)

SoTa: Soft Tactile Skins for Dexterous Manipulation (arxiv.org)

NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches (arxiv.org)

Becoming Suspicious Across Borders: Algorithmic Extraterritoriality and AI-Driven Financial Surveillance (arxiv.org)

Jumping the Line: Exploiting Length Predictions in LLM Scheduling (arxiv.org)

A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control (arxiv.org)

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability (arxiv.org)

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling (arxiv.org)

MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication (arxiv.org)

Reasoning Models Are Accurate but Unsound on Identification (arxiv.org)

From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data (arxiv.org)

Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis (arxiv.org)

Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows (arxiv.org)

Clinical Concept Centers in LLMs (arxiv.org)

Energy Saving in 5G and Beyond Networks: A Quantum Reinforcement Learning Approach (arxiv.org)

Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations (arxiv.org)

SD-DPC: Sparse Dictionary Differentiable Predictive Control (arxiv.org)

Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents (arxiv.org)

IGNITE Tokamak World Model Architecture (arxiv.org)

Learning to Assess Heartbeat Observability for mmWave Heart-Rate Sensing (arxiv.org)

HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents (arxiv.org)

HazardWeaver: Scientific Route Selection for Hazard Analysis Agents (arxiv.org)

Low-Cost Video--Time Priors as a Strong Baseline for EEG--fNIRS Emotion Regression on Familiar Videos (arxiv.org)

Depth as Time in One-Step Generative Models (arxiv.org)

Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI (arxiv.org)

CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization (arxiv.org)

Learning Closure of Dynamical Systems with Kernel Ridge Regression (arxiv.org)

MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search (arxiv.org)

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies (arxiv.org)

FASTDIAR: Frame-level speaker encoder for Streaming Diarization (arxiv.org)

NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents (arxiv.org)

Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents (arxiv.org)

Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System (arxiv.org)

DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering (arxiv.org)

A hybrid CNN-adjoint optimization framework for reconstruction of viscoelastic tissue properties in magnetic resonance elastography (arxiv.org)

Where Quantum Fourier Sampling Stops Short: A Three-Gate Audit Protocol for Delay-PUF Security Models (arxiv.org)

IntentCoding: Amplifying User Intent in Code Generation (arxiv.org)

Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework (arxiv.org)

ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation (arxiv.org)

GlanceWAM: Sparse Test-Time Imagination for World-Action Models (arxiv.org)

CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation (arxiv.org)

When Normalization Selects the Sign: Auditing Robustness Ablations in Quantum Attention (arxiv.org)

Large Language Continuous Diffusion Models (arxiv.org)

Characterizing the Performance Gap in Human Activity Recognition for Older Adults (arxiv.org)

WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds (arxiv.org)

A Missing Latent, Not a Missing Simulator: Radius-Augmented Inference for Real JWST Retrieval (arxiv.org)

Causal discovery identifies pathways linking physical activity to dementia risk in the UK BioBank (arxiv.org)