AI News

Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow (arxiv.org)

MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning (arxiv.org)

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach (arxiv.org)

"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It (arxiv.org)

Multi-Term Fourier Graph Neural Network with Sample Relationship Learning for Enhanced Remaining Useful Life Prediction (arxiv.org)

Label-Efficient Learning for Ground-Based Sky-Image Classification: A Benchmark of Transfer Learning, Active Learning, and Pseudo-Labeling on GCD (arxiv.org)

Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference (arxiv.org)

BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction (arxiv.org)

A Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories (arxiv.org)

Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models (arxiv.org)

Partner-Specific Affective Precision in Social Active Inference (arxiv.org)

TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling (arxiv.org)

Towards Hierarchical GNNs for multi-grid power flow: generalization across operating scenarios (arxiv.org)

Signed Graph Pre-Training and Prompt Learning (arxiv.org)

Stable Unsupervised Continual Chunking with Sheaf SyncMap (arxiv.org)

Discovering Data Manifold Geometry through Geometric Properties (arxiv.org)

Quantum Model Parallelism for MRI-Based Classification of Alzheimer's Disease Stages (arxiv.org)

Relative Wasserstein Angle and the Problem of the $W_2$-Nearest Gaussian Distribution (arxiv.org)

Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection (arxiv.org)

Notes on Fourier-Bessel wavelets (arxiv.org)

MedRSI: Recursive Self-Improvement for Medical Agents via Clinically Aligned Self-Evolution (arxiv.org)

GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes (arxiv.org)

Convex AI Compositionality and the Governance of AI System Populations (arxiv.org)

Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents (arxiv.org)

TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction (arxiv.org)

Beyond Endpoint Performance: Process-Level Evaluation of Self-Evolving Agents (arxiv.org)

Optimizing Canaries for Privacy Auditing with Metagradient Descent (arxiv.org)

FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning (arxiv.org)

When Recursive Models Finish Computing (arxiv.org)

Hierarchical Sparse Bayesian Multitask Learning for Disease Prediction in Pooled Microbiome Studies (arxiv.org)

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy (arxiv.org)

DeepSPoC: A Deep Learning Based Sequential Propagation of Chaos (arxiv.org)

Custom Named Entity Recognition and Topic Classification for Global Health Publications (arxiv.org)

Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis (arxiv.org)

Can We Predict Anomaly Detection Performance from Embedding-Space Geometry? (arxiv.org)

The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence (arxiv.org)

Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information (arxiv.org)

VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning (arxiv.org)

Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs (arxiv.org)

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue (arxiv.org)

DeepFEAv2: Deep Learning for Transient Finite Element Analysis Beyond Structured Meshes (arxiv.org)

OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery (arxiv.org)

CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents (arxiv.org)

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors (arxiv.org)

Diffusion-Induced Spatial Attention Overlapping Community Detection (arxiv.org)

Double Descent and Malign Overfitting in Diffusion Models (arxiv.org)

TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series (arxiv.org)

Learning 3D biophysical cell properties from 2D images and cell-population statistics (arxiv.org)

Learning to Defer with Guidance on Real World Medical Data (arxiv.org)

FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks (arxiv.org)