5 papers
MemArchitect: A Policy Driven Memory Governance Layer
Lingavasan Suresh Kumar, Yang Ba, Rong Pan
Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive…
Measuring Dataset Diversity from a Geometric Perspective
Yang Ba, Mohammad Sadeq Abolhasani, Michelle V Mancenido +1
Diversity can be broadly defined as the presence of meaningful variation across elements, which can be viewed from multiple perspectives, including statistical variation and geomet…
Predict Training Data Quality via Its Geometry in Metric Space
Yang Ba, Mohammad Sadeq Abolhasani, Rong Pan
High-quality training data is the foundation of machine learning and artificial intelligence, shaping how models learn and perform. Although much is known about what types of data…
Fill In The Gaps: Model Calibration and Generalization with Synthetic Data
Yang Ba, Michelle V. Mancenido, Rong Pan
As machine learning models continue to swiftly advance, calibrating their performance has become a major concern prior to practical and widespread implementation. Most existing cal…
Data Diversity as Implicit Regularization: How Does Diversity Shape the Weight Space of Deep Neural Networks?
Yang Ba, Michelle V. Mancenido, Rong Pan
Data augmentation that introduces diversity into the input data has long been used in training deep learning models. It has demonstrated benefits in improving robustness and genera…