AI News

Ownership in AI-Assisted Everyday Tasks (arxiv.org)

PAA: The Probabilistic Allen Algebra: A Generative and Complete Probabilistic Extension of Allen's Interval Relations (arxiv.org)

Limits of Confidence in Diffusion (arxiv.org)

Language-model groups overstate consensus when replaying human deliberation on a reasoning task (arxiv.org)

SoftTri: Smooth Triangular Membership Functions for Adaptive Fuzzy Inference Systems (arxiv.org)

Robust Federated Q-Learning with Almost No Communication (arxiv.org)

Support Thresholds, Not Algorithms, Limit Rare-Association Recovery in Co-Purchase Networks (arxiv.org)

Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization (arxiv.org)

A Noise Optimum in Rehearsal-Free Continual Learning: Isolation, Mechanism, and Scope (arxiv.org)

Fast-varying Natural Frequencies and Damping Ratio Identification for Linear Time-Varying System (arxiv.org)

Refuse, Decompose, Refresh: A Claim-Safe Protocol for Closed-Loop AI Evaluation (arxiv.org)

FreqCondNorm: Towards Cross-domain Predictive Maintenance through a Frequency-Conditioned Transformer Foundation Model (arxiv.org)

QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization (arxiv.org)

Bridging Modalities on the Cortex: Surface-based MRI to PET Translation with a Diffusion Bridge (arxiv.org)

Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants (arxiv.org)

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness (arxiv.org)

How Do Agent Harnesses Create Value? Planning Information and Release Control in Stateful LLM Agents (arxiv.org)

QoS-Aware Federated Learning for Multimodal In-Cabin Interaction in Smart Vehicles (arxiv.org)

CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning (arxiv.org)

SETTer: Sparse-Encoder Transformer for Long-term Multivariate Time Series Forecasting (arxiv.org)

Evaluating Explanation Methods by the Predictors They Induce (arxiv.org)

CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling (arxiv.org)

SkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback (arxiv.org)

The Organization of Inference: Information, Resource Constraints, and AI Production (arxiv.org)

Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model (arxiv.org)

A Qualitative Model for Reasoning about Path and Support (arxiv.org)

Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG (arxiv.org)

Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation (arxiv.org)

NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction (arxiv.org)

Diagnose, Recover, Certify: Task Readiness under Hidden Dynamics Changes (arxiv.org)

AgentPProf: Semantic Profiler for Long Horizon AI Agents (arxiv.org)

Is It Still Worth Training a Classical Model in the Era of LLMs? A Crossover Benchmark on Tabular Data (arxiv.org)

Transformer fault diagnosis using an efficient simulation-driven variational quantum classifier with domain-aware feature encoding (arxiv.org)

VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots (arxiv.org)

LEO Satellite Internet of Things: Architecture, Technology, and On-Orbit Verification (arxiv.org)

AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair (arxiv.org)

Local Sparsity Enables Unsupervised LLM Safety Detection (arxiv.org)

Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis (arxiv.org)

SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership (arxiv.org)

Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks (arxiv.org)

When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent R\'esum\'e Screening (arxiv.org)

Self Improvement via Fast Tree-search (arxiv.org)

A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems (arxiv.org)

EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data (arxiv.org)

ZeroHAT: Behavior-Conditioned Zero-Shot Human Activity Trace Generation (arxiv.org)

Hypernetwork-Parameterized Spatially Adaptive Neural Operators for PDE Learning (arxiv.org)

FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity (arxiv.org)

WiCleanData: Guaranteeing the Type Consistency of Wikidata by Taxonomy Refinement and Constraint Enforcement (arxiv.org)

MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution (arxiv.org)

Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation (arxiv.org)