5 papers
Krause Synchronization Transformers
Jingkun Liu, Yisong Yue, Max Welling +1
Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interacti…
Kuramoto Orientation Diffusion Models
Yue Song, T. Anderson Keller, Sevan Brodjian +4
Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular directional patterns that are challenging to model using standard generative approaches b…
Langevin Flows for Modeling Neural Latent Dynamics
Yue Song, T. Anderson Keller, Yisong Yue +2
Neural populations exhibit latent dynamical structures that drive time-evolving spiking activities, motivating the search for models that capture both intrinsic network dynamics an…
Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning
Fengze Xie, Sizhe Wei, Yue Song +2
We present a morphological-symmetry-equivariant heterogeneous graph neural network, namely MS-HGNN, for robotic dynamics learning, that integrates robotic kinematic structures and…
Unsupervised Representation Learning from Sparse Transformation Analysis
Yue Song, Thomas Anderson Keller, Yisong Yue +2
There is a vast literature on representation learning based on principles such as coding efficiency, statistical independence, causality, controllability, or symmetry. In this pape…