AI News

Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching (arxiv.org)

Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning (arxiv.org)

DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors (arxiv.org)

TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Models (arxiv.org)

AutoMine Solution for AV2 2026 Scenario Mining Challenge (arxiv.org)

Structure-Preserving Neural Surrogates with Tractable Uncertainty Quantification (arxiv.org)

Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents (arxiv.org)

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning (arxiv.org)

Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices (arxiv.org)

Augmenting Molecular Language Models with Local $n$-gram Memory (arxiv.org)

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation (arxiv.org)

On Subquadratic Architectures: From Applications to Principles (arxiv.org)

Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy (arxiv.org)

CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy (arxiv.org)

Position: Hippocampal Explicit Memory Is the Cornerstone for AGI (arxiv.org)

StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery (arxiv.org)

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning (arxiv.org)

From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference (arxiv.org)

Can AI Agents Synthesize Scientific Conclusions? (arxiv.org)

Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents (arxiv.org)

Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline (arxiv.org)

INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration (arxiv.org)

Forecasting Future Behavior as a Learning Task (arxiv.org)

Search Discipline for Long-Horizon Research Agents (arxiv.org)

MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning (arxiv.org)

Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation (arxiv.org)

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization (arxiv.org)

Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds (arxiv.org)

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent (arxiv.org)

Neural-Parameterized Cellular Automata for Wildfire Spread (arxiv.org)

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting (arxiv.org)

Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents (arxiv.org)

Visualizing LLM Latent Space Geometry Through Dimensionality Reduction (arxiv.org)

When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis (arxiv.org)

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (arxiv.org)

Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study (arxiv.org)

Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model (arxiv.org)

Making Foresight Actionable: Repurposing Representation Alignment in World Action Models (arxiv.org)

Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends (arxiv.org)

Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation (arxiv.org)

PAWS: Preference Learning with Advantage-Weighted Segments (arxiv.org)

HAMNO: A Hierarchical Adaptive Multi-scale Neural Operator with Physics-Informed Learning for Dynamical Systems (arxiv.org)

Beyond representational alignment with brain-guided language models for robust reasoning (arxiv.org)

MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry (arxiv.org)

Attention by Synchronization in Coupled Oscillator Networks (arxiv.org)

RePAIR: Predictive Self-Supervised Representation Learning in Chess (arxiv.org)

Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations (arxiv.org)

NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track (arxiv.org)

The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content (arxiv.org)

MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation (arxiv.org)