Evaluating Graph Neural Networks for Bitcoin Fraud Detection
Discover why Graph Neural Networks may underperform in Bitcoin fraud detection under temporal shifts and how feature-only models excel.
EVPO: Adaptive Policy Optimization for LLM Post-Training
Discover EVPO, an adaptive policy optimization method that improves LLM post-training by balancing critic use to reduce variance and boost performance.
Fairness Audits for Institutional ML Risk Models
Explore fairness audits of institutional risk models in ML pipelines, revealing biases by gender, age, and residency in educational support systems.
Neural Operator Framework for Stability in Physical Systems
Discover a data-driven neural operator framework that analyzes stability and receptivity in complex physical systems without traditional equations.
LePREC: Enhanced Legal Issue Identification with AI
LePREC improves legal issue identification by combining neural and symbolic AI, boosting accuracy by 30-40% over traditional LLM methods.