AI News

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

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

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

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

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

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

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

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

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

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

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

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

World State Generator (arxiv.org)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Brain-Inspired Hierarchical Modularity for General Continual Learning (arxiv.org)

Et Tu, Brute? Economic Misalignment in Personal AI Agents (arxiv.org)

Emergent Collusion in Long-Horizon LLM Agent Interaction (arxiv.org)

Harness-Zero: Harness Distillation via Agent-as-Harness (arxiv.org)

AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos (arxiv.org)

LLM-based Conversational AI Knowledge Assistant for MyBuddy Humanoid Robot (arxiv.org)

Polyak-Type Extragradient Methods for Monotone Root-Finding Problems (arxiv.org)

MT-ProtBERT: Multi-task Learning ProtBERT for Intrinsically Disordered Proteins Classification with Scarce Data (arxiv.org)

Concept Drift from a Causal Perspective (arxiv.org)

Extending FunctionGemma for Practical On-Device Mobile Function Calling (arxiv.org)

Deep Reinforcement Learning on Item-Compatibility Graphs for One-Dimensional Bin Packing (arxiv.org)

Predictive Uncertainty for Neural CAE Surrogates (arxiv.org)

Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems (arxiv.org)

PermuFormer: Multi-Task Pretraining for Permutation Representation in Algebraic Combinatorics (arxiv.org)

Mean Velocity Matching: Rethinking Generative Dynamics in Diffusion Models (arxiv.org)

Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining (arxiv.org)

Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy (arxiv.org)

Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training (arxiv.org)

The Wisdom of Artificial Deliberative Crowds (arxiv.org)