3 papers
cs.LG2026
Deep Minds and Shallow Probes
Su Hyeong Lee, Risi Kondor
Neural representations are not unique objects. Even when two systems realize the same downstream computation, their hidden coordinates may differ by reparameterization. A probe fam…
cs.LG2026
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
Su Hyeong Lee, Risi Kondor, Richard Ngo
We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log…
cs.LG2025
On Defining Neural Averaging
Su Hyeong Lee, Richard Ngo
What does it even mean to average neural networks? We investigate the problem of synthesizing a single neural network from a collection of pretrained models, each trained on disjoi…