David Bau

Northeastern University — United States

Computer Science · Physical Sciences

29h-index7.6kcitations126works4.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Generative Adversarial Networks and Image Synthesis(28), Topic Modeling(22), Explainable Artificial Intelligence (XAI)(21), Natural Language Processing Techniques(16), Adversarial Robustness in Machine Learning(14)

Publications123 total

In-Context Algebra
arXiv (Cornell University)·2025Open Access
In-Context Algebra
ArXiv.org·2025Open Access
Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions
Lecture notes in computer science·2025· 1 citedOpen Access
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis
Computational Linguistics·2025Open Access
Hidden Layers: An Interactive Installation for Exploring the Neural Semantics of Image Synthesis
2025Open Access
LLMs Encode Harmfulness and Refusal Separately
arXiv (Cornell University)·2025Open Access
Discovering Forbidden Topics in Language Models
arXiv (Cornell University)·2025Open Access
When Are Concepts Erased From Diffusion Models?
arXiv (Cornell University)·2025Open Access
Language Models use Lookbacks to Track Beliefs
arXiv (Cornell University)·2025Open Access
MIB: A Mechanistic Interpretability Benchmark
arXiv (Cornell University)·2025Open Access
Distilling Diversity and Control in Diffusion Models
arXiv (Cornell University)·2025Open Access
Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
arXiv (Cornell University)·2025Open Access
Position-aware Automatic Circuit Discovery
arXiv (Cornell University)·2025Open Access
SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
arXiv (Cornell University)·2025· 1 citedOpen Access
Open Problems in Mechanistic Interpretability
arXiv (Cornell University)·2025· 5 citedOpen Access
Position-aware Automatic Circuit Discovery
2025Open Access
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
SSRN Electronic Journal·2025Open Access
Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
2025Open Access
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice
SSRN Electronic Journal·2025· 5 citedOpen Access
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
arXiv (Cornell University)·2024Open Access
page 1 of 7Next →

Frequent Co-authors

Antonio Torralba(20), Bolei Zhou(13), Jun-Yan Zhu(9), Aude Oliva(7), Hendrik Strobelt(6), Alex Andonian(4), Joanna Materzyńska(4), Leilani H. Gilpin(3), Ben Z. Yuan(3), Ayesha Bajwa(3), Lalana Kagal(3), Joshua B. Tenenbaum(3), William T. Freeman(3), Yonatan Belinkov(3), Rohit Gandikota(3), Sheng-Yu Wang(3), Lloyd N. Trefethen(2), Jeff Gray(2), Caitlin Kelleher(2), Josh Sheldon(2)