Brandon J McMahan — accepted AI-conference papers

2024

Shared Autonomy with IDA: Interventional Diffusion Assistance

Brandon J McMahan, Zhenghao Peng, Bolei Zhou, Jonathan Kao

NeurIPS 2024poster

The rapid development of artificial intelligence (AI) has unearthed the potential to assist humans in controlling advanced technologies. Shared autonomy (SA) facilitates control by combining inputs from a human pilot and an AI copilot. In prior SA studies, the copilot is constantly active in determi…

Cited by 1 Source ↗PDF ↗Scholar ↗

2021

Learning rule influences recurrent network representations but not attractor structure in decision-making tasks

Brandon J McMahan, Michael Kleinman, Jonathan Kao

NeurIPS 2021poster

Recurrent neural networks (RNNs) are popular tools for studying computational dynamics in neurobiological circuits. However, due to the dizzying array of design choices, it is unclear if computational dynamics unearthed from RNNs provide reliable neurobiological inferences. Understanding the effects…

Cited by 6 Source ↗PDF ↗Scholar ↗