Meta Introduces RankGraph-2 Framework for Billion-Node Graph-Based Recommendation Retrieval
Researchers Develop Skew Polynomial Framework for Division Algebras and Maximum Rank Distance Codes
Study Reveals Time Series Foundation Models Hide Critical Failures in Traffic Forecasting
SafeClawBench: New Benchmark Separates Semantic Acceptance from Actual Harm in LLM Agent Security
ThousandWorlds: New Machine Learning Benchmark for Exoplanet Climate Modeling
ReSYNC: New Approach Enables Robots to Learn from Failures and Avoid Future Errors
New Research Method Improves AI Model Transparency and Safety Through Self-Consistency Training
RGNet: Neural Network Architecture Using Renormalization Group for Imbalanced Fault Diagnosis
Researchers Achieve Near-Zero Catastrophic Failures in Neural-Codec Text-to-Speech Systems
Researchers Propose K-Hop Gaussian Diffusion to Enhance Graph Neural Networks
Survey on AI-Driven Models for Soil Moisture Estimation and Classification
Ghost Attractor Networks: Efficient Dynamical Decoder for Robotic Control
New Computational Geometry Paper Introduces Repair Entropy for Dynamic Nearest-Neighbour Structures
TRIDENT: New Framework Enables Provably Safe Multi-Agent Reinforcement Learning in Cyber-Physical Systems
DRIFT: New Method for Optimizing Training Data in Large Language Models
New Neural Operator Framework Advances High-Fidelity Solutions for Complex Mathematical Problems
New Pruning Method Enables Efficient Compression of Mixture-of-Experts AI Models
Researchers Link Shock-wave Theory to Neural Network Training Dynamics
Research Paper Proposes Design Method for Identifying Reusable Metadata in Property Graph Schemas
Research Paper Evaluates "Vibe Coding" Approach to AI-Driven Software Development