Continuous Manifold Alignment via Dual VAEs
Reformulating continuous trajectory translation as an online geometric regression problem. This framework bridges two latent manifolds using frozen Dual VAEs and a novel O(N · D) temporal path integration algorithm to eliminate catastrophic forgetting.
Elastic Homeostasis in Spiking Neural Networks
Can learning emerge from adaptive equilibrium points rather than synaptic weights? Testing a novel hypothesis where neurons maintain stable firing patterns but can shift to new equilibria under sustained perturbation. Implemented 100k neuron simulation using homeostatic Izhikevich model.
Minimal World Model Formation
Can an AI develop functional world understanding from a single temporal signal? Challenging the assumption that models need pre-structured data. Testing if world models can bootstrap from one value changing over time through predictive coding and continuous architectural plasticity.