
Researcher · Academic
Northeastern UniversityAssistant Professor of Computer Science
David Bau helped develop Network Dissection to identify what individual parts of an image recognition model respond to.[1] He co-created ROME, a way to edit specific facts in a language model.[2] He directs the National Deep Inference Fabric, which gives researchers access to the inner workings of large AI models.[3]
Northeastern University2022-present
Harvard University2021-2022
Google2004-2016Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Bau describes how Network Dissection identifies the concepts that individual units respond to.
Credits Bau as an equal contributor and describes ROME’s method for editing factual associations.
Identifies Bau as NDIF director and describes its work on opening AI models to study.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.