6 papers
Emergence of Hierarchical Emotion Organization in Large Language Models
Maya Okawa, Bo Zhao, Eric J. Bigelow +4
As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment. Inspired by emoti…
Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success
Luca Zhou, Bo Zhao, Rose Yu +1
Model merging combines knowledge from separately fine-tuned models, yet the factors driving its success remain poorly understood. While recent work treats mergeability as an intrin…
A Survey of Weight Space Learning: Understanding, Representation, and Generation
Xiaolong Han, Zehong Wang, Bo Zhao +8
Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances…
Symmetry in Neural Network Parameter Spaces
Bo Zhao, Robin Walters, Rose Yu
Modern deep learning models are highly overparameterized, resulting in large sets of parameter configurations that yield the same outputs. A significant portion of this redundancy…
Understanding Mode Connectivity via Parameter Space Symmetry
Bo Zhao, Nima Dehmamy, Robin Walters +1
Neural network minima are often connected by curves along which train and test loss remain nearly constant, a phenomenon known as mode connectivity. While this property has enabled…
Improving Learning to Optimize Using Parameter Symmetries
Guy Zamir, Aryan Dokania, Bo Zhao +1
We analyze a learning-to-optimize (L2O) algorithm that exploits parameter space symmetry to enhance optimization efficiency. Prior work has shown that jointly learning symmetry tra…