Associate Investigator, Allen Institute
2 papers at NeurIPS 2025
The volume transmission of small molecules implements a context-factorized hypernetwork capable of online credit assignment and compositional learning reminiscent of neurobiology.
Using simple DNNs with dendrite-inspired architectures, we show that single neurons exhibit a morphology-driven phase transition in learnability, with robustness–adaptability trade-offs that suggest new inductive biases for NeuroAI model design.
