David Bau
(he/him/his)
Assistant Professor
Research interests
- Machine learning
- Computer vision
- Artificial intelligence
- Natural language processing
- Human–computer interaction
Education
- PhD in Computer Science, Massachusetts Institute of Technology
- MS in Computer Science, Cornell University
- AB in Mathematics, Harvard University
Biography
David Bau is an assistant professor in the Khoury College of Computer Sciences at Northeastern University, based in Boston.
Bau's research focuses on human-computer interaction and machine learning. Before joining Northeastern, he worked as a software engineer at Google, BEA, and Crossgain. He has been published in journals such as CVPR, NeurIPS, ICCV, ECCV, and SIGGRAPH.
Outside of research, Bau enjoys astronomy and puzzle collecting.
Recent publications
-
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
Citation: Sheridan Feucht, David Atkinson, Byron C. Wallace, David Bau. (2024). Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs EMNLP, 9727-9739. https://aclanthology.org/2024.emnlp-main.543 -
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
Citation: Nikhil Prakash, Tamar Rott Shaham, Tal Haklay, Yonatan Belinkov, David Bau. (2024). Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking ICLR. https://openreview.net/forum?id=8sKcAWOf2D -
Function Vectors in Large Language Models
Citation: Eric Todd, Millicent L. Li, Arnab Sen Sharma, Aaron Mueller, Byron C. Wallace, David Bau. (2024). Function Vectors in Large Language Models ICLR. https://openreview.net/forum?id=AwyxtyMwaG -
Linearity of Relation Decoding in Transformer Language Models
Citation: Evan Hernandez, Arnab Sen Sharma, Tal Haklay, Kevin Meng, Martin Wattenberg, Jacob Andreas, Yonatan Belinkov, David Bau. (2024). Linearity of Relation Decoding in Transformer Language Models ICLR. https://openreview.net/forum?id=w7LU2s14kE -
Erasing Concepts from Diffusion Models
Citation: Rohit Gandikota, Joanna Materzynska, Jaden Fiotto-Kaufman, David Bau. (2023). Erasing Concepts from Diffusion Models ICCV, 2426-2436. https://doi.org/10.1109/ICCV51070.2023.00230 -
Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
Citation: Pal, K., Sun, J., Yuan, A., Wallace, B.C., & Bau, D. (2023). Future Lens: Anticipating Subsequent Tokens from a Single Hidden State. ArXiv, abs/2311.04897. -
FIND: A Function Description Benchmark for Evaluating Interpretability Methods
Citation: Sarah Schwettmann, Tamar Rott Shaham, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba . (2023). FIND: A Function Description Benchmark for Evaluating Interpretability Methods NeurIPS. http://papers.nips.cc/paper_files/paper/2023/hash/ef0164c1112f56246224af540857348f-Abstract-Datasets_and_Benchmarks.html -
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Citation: Kenneth Li , Aspen K. Hopkins, David Bau, Fernanda B. Viégas, Hanspeter Pfister, Martin Wattenberg. (2023). Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task ICLR. https://openreview.net/pdf?id=DeG07_TcZvT -
Mass-Editing Memory in a Transformer
Citation: Kevin Meng, Arnab Sen Sharma, Alex J. Andonian, Yonatan Belinkov, David Bau. (2023). Mass-Editing Memory in a Transformer ICLR. https://openreview.net/pdf?id=MkbcAHIYgyS -
Toward a Visual Concept Vocabulary for GAN Latent Space
Citation: Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba . (2021). Toward a Visual Concept Vocabulary for GAN Latent Space ICCV, 6784-6792. https://doi.org/10.1109/ICCV48922.2021.00673 -
Locating and Editing Factual Associations in GPT
Citation: Meng, K., Bau, D., Andonian, A., & Belinkov, Y. (2022). Locating and Editing Factual Associations in GPT. Neural Information Processing Systems. -
Disentangling visual and written concepts in CLIP
Citation: Joanna Materzynska, Antonio Torralba , David Bau. (2022). Disentangling visual and written concepts in CLIP CVPR, 16389-16398. https://doi.org/10.1109/CVPR52688.2022.01592 -
Sketch Your Own GAN
Citation: Sheng-Yu Wang, David Bau, and Jun-Yan Zhu. Sketch Your Own GAN. Proceedings of the IEEE/CVF International Conference on Computer Vision. (ICCV 2021) -
Diverse Image Generation via Self-Conditioned GANs
Citation: Steven Liu, Tongzhou Wang , David Bau, Jun-Yan Zhu, Antonio Torralba . (2020). Diverse Image Generation via Self-Conditioned GANs CVPR, 14274-14283. https://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Diverse_Image_Generation_via_Self-Conditioned_GANs_CVPR_2020_paper.html
