5 papers
Do Large Language Models Capture the Diversity in their Training Data?
Youqi Wu, Farzan Farnia
Large language models are trained to model conditional distributions over text, yet it remains inadequately understood whether they capture the full diversity of plausible outputs…
KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models
Youqi Wu, Mohammad Jalali, Farzan Farnia
Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems. While these models are typically compared through dow…
The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning
Youqi Wu, Farzan Farnia
Von Neumann entropy (VNE) is a fundamental quantity in quantum information theory and has recently been adopted in machine learning as a spectral measure of diversity for kernel ma…
When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
Youqi Wu, Jingwei Zhang, Farzan Farnia
State-of-the-art embeddings often capture distinct yet complementary discriminative features: For instance, one image embedding model may excel at distinguishing fine-grained textu…
Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning
Chih Wei Ling, Chun Hei Michael Shiu, Youqi Wu +4
Training machine learning models on decentralized private data via federated learning (FL) poses two key challenges: communication efficiency and privacy protection. In this work,…