Elamur Research⌕
☰
home / authors / David Bau

David Bau

David Bau has 3 papers in our library, in 2023–2026, most of them on Interpretability; often with Arnab Sen Sharma, Jiuding Sun, Koyena Pal.

3 papers in our library · 2023–2026

OpenAlex · ORCID · Wikidata · h-index 32 · 106 works · 13,913 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 1,328 times in our library · 7 more in our library without a page yet · ⭐ Paper Stars ranking: #7253

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Northeastern UniversityBoston · United States2022–2026 · 56 papersEmployment since 2022 · Assistant Professor, Khoury College of Computer Sciencecurrent🎓Massachusetts Institute of TechnologyCambridge · United States2015–2021 · 23 papersEducationEmployment 2015–2021 · Research Assistatnt, CSAIL🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2017–2025 · 19 papers🏢MicrosoftRedmond · United States1993–2022 · 12 papersEmployment 1993–2000🏢GoogleMountain View · United States2004–2016 · 4 papersEmployment 2004–2016 · Staff Software Engineer🎓Phillips Exeter AcademyExeter · United States2014–2015 · 2 papers🎓Cornell UniversityIthaca · United States1992–2001 · 2 papersEducation 1992–1994 · Masters of Science, Computer Science🎓Harvard UniversityCambridge · United States1988–2022 · 1 paperEducation 1988–1992 · Bachelor of Arts, MathematicsEmployment 2021–2022 · Postdoctoral Associate, Computer Science
🏛️National Deep Inference FabricBoston · United States2024Employment since 2024 · Director
🏛️Harvard CollegeCambridge · United States1988–1992Education 1988–1992

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 1Research subjects and languages the work is about.Interpretability · 1 work

 Works by year

2020s

20261 paper20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Future Lens: Anticipating Subsequent Tokens from a Single Hidden State (2023 · 49 citations)
    The paper asks whether a transformer's internal state for one token carries information about tokens beyond the immediate next one, specifically positions t+2 and later. Working with GPT-J-6B, the authors compare three ways of reading that information out of a single hidden state taken at one layer and one position.
  2. Locating and Editing Factual Associations in Mamba (2024 · 18 citations)
    Studies of transformer LMs have found that factual recall is concentrated in particular modules at specific token positions, and that one rank-one weight change can overwrite a stored fact.
  3. The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis (2026 · 7 citations)
    Research on mechanistic interpretability (MI) of language models is fragmented. Studies use bespoke evaluations, lack a shared theoretical basis, and rarely define the elementary causal units that make up a "mechanism." This survey, published in Computational Linguistics, treats MI as recovering causal graphs that…

All works

10 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Network Dissection: Quantifying Interpretability of Deep Visual Representations ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetDavid Anthony Bau et al.2017 · 1,396 citations
  2. Locating and Editing Factual Associations in GPT ↗arXiv:2202.05262 · no summary yetKevin Meng et al.2022 · 1,124 citations
  3. Erasing Concepts from Diffusion Models ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetRohit Gandikota et al.2023 · 277 citations
  4. Function Vectors in Large Language Models ↗arXiv:2310.15213 · no summary yetEric Todd et al.2023 · 127 citations
  5. Linearity of Relation Decoding in Transformer Language Models ↗arXiv:2308.09124 · no summary yetEvan Hernandez et al.2023 · 82 citations
  6. Future Lens: Anticipating Subsequent Tokens from a Single Hidden StateConference on Computational Natural Language Learning (CoNLL)Koyena Pal, Jiuding Sun, Andrew Yuan, et al.2023 · 49 citations
  7. Locating and Editing Factual Associations in MambaarXiv:2404.03646Arnab Sen Sharma, David Atkinson, David Bau2024 · 18 citations
  8. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice ↗SSRN Electronic Journal · no summary yetA. Feder Cooper et al.2025 · 12 citations
  9. The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation AnalysisComputational LinguisticsAaron Mueller, Jannik Brinkmann, Millicent Li, et al.2026 · 7 citations
  10. Shared Lexical Task Representations Explain Behavioral Variability In LLMs ↗arXiv (Cornell University) · no summary yetZhuonan Yang et al.2026

 Co-authors here

6 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 1,328 times (of the 149,439 papers whose bibliographies we read); 195 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/david-bau/