Research
- A Spacetime Perspective on Dynamical Computation in Neural Information Processing Systems
- Relative Representations for Model-to-Brain Mappings
- Natural Inductive Biases for Artificial Intelligence (PhD Thesis)
- Image Segmentation with Complex Valued Kuramoto Models
- Flow Factorized Representation Learning
- Traveling Waves Encode the Recent Past and Enhance Sequence Learning
- DEUT -- 2D Structured and Approximately Equivariant Representations
- Latent Traversals in Generative Models as Potential Flows
- Locally Coupled Oscillatory Recurrent Networks Learn Topographic Organization
- Neural Wave Machines
- Homomorphic Self-Supervised Learning
- Modeling Category-Selective Cortical Regions with Topographic VAEs
- Predictive Coding with Topographic VAEs
- Topographic VAEs learn Equivariant Capsules
- As Easy as APC
- Self Normalizing Flows
- Fast Weight Long Short-Term Memory