AI News

⚡ 5 minutes ago
1
1
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching (arxiv.org)
2
1
Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning (arxiv.org)
3
1
DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors (arxiv.org)
4
1
TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Models (arxiv.org)
5
1
AutoMine Solution for AV2 2026 Scenario Mining Challenge (arxiv.org)
6
1
Structure-Preserving Neural Surrogates with Tractable Uncertainty Quantification (arxiv.org)
7
1
Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents (arxiv.org)
8
1
From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning (arxiv.org)
9
1
Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices (arxiv.org)
10
1
Augmenting Molecular Language Models with Local $n$-gram Memory (arxiv.org)
11
1
Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation (arxiv.org)
12
1
On Subquadratic Architectures: From Applications to Principles (arxiv.org)
13
1
Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy (arxiv.org)
14
1
CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy (arxiv.org)
15
1
Position: Hippocampal Explicit Memory Is the Cornerstone for AGI (arxiv.org)
16
1
StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery (arxiv.org)
17
1
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning (arxiv.org)
18
1
From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference (arxiv.org)
19
1
Can AI Agents Synthesize Scientific Conclusions? (arxiv.org)
20
1
Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents (arxiv.org)
21
1
Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline (arxiv.org)
22
1
INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration (arxiv.org)
23
1
Forecasting Future Behavior as a Learning Task (arxiv.org)
24
1
Search Discipline for Long-Horizon Research Agents (arxiv.org)
25
1
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning (arxiv.org)
26
1
Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation (arxiv.org)
27
1
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization (arxiv.org)
28
1
Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds (arxiv.org)
29
1
Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent (arxiv.org)
30
1
Neural-Parameterized Cellular Automata for Wildfire Spread (arxiv.org)
31
1
CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting (arxiv.org)
32
1
Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents (arxiv.org)
33
1
Visualizing LLM Latent Space Geometry Through Dimensionality Reduction (arxiv.org)
34
1
When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis (arxiv.org)
35
1
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (arxiv.org)
36
1
Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study (arxiv.org)
37
1
Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model (arxiv.org)
38
1
Making Foresight Actionable: Repurposing Representation Alignment in World Action Models (arxiv.org)
39
1
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends (arxiv.org)
40
1
Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation (arxiv.org)
41
1
PAWS: Preference Learning with Advantage-Weighted Segments (arxiv.org)
42
1
HAMNO: A Hierarchical Adaptive Multi-scale Neural Operator with Physics-Informed Learning for Dynamical Systems (arxiv.org)
43
1
Beyond representational alignment with brain-guided language models for robust reasoning (arxiv.org)
44
1
MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry (arxiv.org)
45
1
Attention by Synchronization in Coupled Oscillator Networks (arxiv.org)
46
1
RePAIR: Predictive Self-Supervised Representation Learning in Chess (arxiv.org)
47
1
Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations (arxiv.org)
48
1
NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track (arxiv.org)
49
1
The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content (arxiv.org)
50
1
MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation (arxiv.org)