Unified Benchmark for Knowledge Graphs & GNN Evaluation
Discover a unified benchmark to evaluate knowledge graph construction methods and graph neural networks in biomedical AI applications.
Using AI Mistakes to Boost Critical Thinking Skills
Discover how AI errors in education can enhance critical thinking, metacognition, and AI literacy for deeper student engagement and learning.
Robust Graph Self-Supervised Learning for Noisy Biomedical Text
Explore robust graph self-supervised learning methods for noisy biomedical text-driven graphs, improving accuracy by up to 7% over language models.
SLAM: Advanced Watermarking for High-Quality Language Models
Discover SLAM, a novel watermarking method for language models that ensures high detection accuracy with minimal impact on text quality.
Semantic Loss Fine-Tuning to Prevent Model Collapse
Discover how semantic loss fine-tuning prevents model collapse and improves causal reasoning accuracy in transformer AI models.