Saliency-Aware Quantization for Efficient Large Language Models
Discover SARQC, a saliency-aware quantization method that improves large language model efficiency without extra computational cost or performance loss.
GCCM: Boosting Generative Graph Prediction Accuracy
Discover how GCCM improves generative graph prediction using contrastive consistency to enhance accuracy and stability in AI models.
DataDignity: Provenance Attribution for Large Language Models
Discover DataDignity, a breakthrough framework for training data attribution that enhances transparency and accuracy in large language models.
Transformer Memory Geometry: Resolving Conflicts & Hallucinations
Explore how transformer models handle memory conflicts and hallucinations using attractor geometry for improved AI reliability and accuracy.
Mitigating Safety Risks in Large Reasoning Models with Adaptive Steering
Explore safety risks in large reasoning AI models and how adaptive multi-principle steering reduces harmful outputs while maintaining accuracy.