Galen Pogoncheff — accepted AI-conference papers

2026

BIRD: Behavior Induction via Representation-structure Distillation

ICLR 2026poster

Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, safety, and fairness. Transferring these behavioral properties to models trained on different tasks or data distributions remains challenging: aligned behavior is easily forgotten during fine-tuni…

Cited by 0 Source ↗Scholar ↗

2023

Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture

Galen Pogoncheff, Jacob Granley, Michael Beyeler

NeurIPS 2023poster

Convolutional neural networks (CNNs) have recently emerged as promising models of the ventral visual stream, despite their lack of biological specificity. While current state-of-the-art models of the primary visual cortex (V1) have surfaced from training with adversarial examples and extensively aug…

Cited by 8 Source ↗PDF ↗Scholar ↗