David Bau

Orcid: 0000-0003-1744-6765

According to our database¹, David Bau authored at least 68 papers between 1997 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Links

On csauthors.net:

Bibliography

2024

Erasing Conceptual Knowledge from Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding of Causal Interpretability.

[BibT_eX]

[DOI]

Aruna Sankaranarayanan

CoRR, 2024

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models.

[BibT_eX]

[DOI]

Claudio Mayrink Verdun

David Bau

Samuel Marks

CoRR, 2024

NNsight and NDIF: Democratizing Access to Foundation Model Internals.

[BibT_eX]

[DOI]

CoRR, 2024

Locating and Editing Factual Associations in Mamba.

[BibT_eX]

[DOI]

Arnab Sen Sharma

David Atkinson

David Bau

CoRR, 2024

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Model Lakes.

[BibT_eX]

[DOI]

Koyena Pal

David Bau

Renée J. Miller

CoRR, 2024

Measuring and Controlling Persona Drift in Language Model Dialogs.

[BibT_eX]

[DOI]

CoRR, 2024

Unified Concept Editing in Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Customizing Text-to-Image Models with a Single Image Pair.

[BibT_eX]

[DOI]

Proceedings of the SIGGRAPH Asia 2024 Conference Papers, 2024

Function Vectors in Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Linearity of Relation Decoding in Transformer Language Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Black-Box Access is Insufficient for Rigorous AI Audits.

[BibT_eX]

[DOI]

Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

Testing methods of neural systems understanding.

[BibT_eX]

[DOI]

Grace W. Lindsay

David Bau

Cogn. Syst. Res., December, 2023

An Alternative to Regulation: The Case for Public AI.

[BibT_eX]

[DOI]

CoRR, 2023

Testing Language Model Agents Safely in the Wild.

[BibT_eX]

[DOI]

CoRR, 2023

A Function Interpretation Benchmark for Evaluating Interpretability Methods.

[BibT_eX]

[DOI]

CoRR, 2023

Discovering Variable Binding Circuitry with Desiderata.

[BibT_eX]

[DOI]

CoRR, 2023

Content-based Search for Deep Generative Models.

[BibT_eX]

[DOI]

Proceedings of the SIGGRAPH Asia 2023 Conference Papers, 2023

FIND: A Function Description Benchmark for Evaluating Interpretability Methods.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mass-Editing Memory in a Transformer.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Multimodal Neurons in Pretrained Text-Only Transformers.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Erasing Concepts from Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Future Lens: Anticipating Subsequent Tokens from a Single Hidden State.

[BibT_eX]

[DOI]

Proceedings of the 27th Conference on Computational Natural Language Learning, 2023

2022

Rewriting geometric rules of a GAN.

[BibT_eX]

[DOI]

Sheng-Yu Wang

David Bau

Jun-Yan Zhu

ACM Trans. Graph., 2022

Content-Based Search for Deep Generative Models.

[BibT_eX]

[DOI]

CoRR, 2022

Local Relighting of Real Scenes.

[BibT_eX]

[DOI]

Shahin Mahdizadehaghdam

Rohit Kumar

David Bau

CoRR, 2022

Locating and Editing Factual Knowledge in GPT.

[BibT_eX]

[DOI]

CoRR, 2022

Locating and Editing Factual Associations in GPT.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

HAI-GEN 2022: 3rd Workshop on Human-AI Co-Creation with Generative Models.

[BibT_eX]

[DOI]

Proceedings of the IUI 2022: 27th International Conference on Intelligent User Interfaces, Helsinki, Finland, March 22 - 25, 2022, 2022

Natural Language Descriptions of Deep Visual Features.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Disentangling visual and written concepts in CLIP.

[BibT_eX]

[DOI]

Joanna Materzynska

Antonio Torralba

David Bau

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Dissection of Deep Neural Networks.

[BibT_eX]

[DOI]

David Bau

PhD thesis, 2021

Paint by Word.

[BibT_eX]

[DOI]

CoRR, 2021

From Droplet to Lilypad: Present and Future of Dual-Modality Environments.

[BibT_eX]

[DOI]

Emma Andrews

David Bau

Jeremiah J. Blanchard

Proceedings of the IEEE Symposium on Visual Languages and Human-Centric Computing, 2021

Editing a classifier by rewriting its prediction rules.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sketch Your Own GAN.

[BibT_eX]

[DOI]

Sheng-Yu Wang

David Bau

Jun-Yan Zhu

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Toward a Visual Concept Vocabulary for GAN Latent Space.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

Understanding the role of individual units in a deep neural network.

[BibT_eX]

[DOI]

Proc. Natl. Acad. Sci. USA, 2020

What Makes Fake Images Detectable? Understanding Properties that Generalize.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Rewriting a Deep Generative Model.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Diverse Image Generation via Self-Conditioned GANs.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Comparing the Interpretability of Deep Networks via Network Dissection.

[BibT_eX]

[DOI]

Proceedings of the Explainable AI: Interpreting, 2019

Semantic photo manipulation with a generative image prior.

[BibT_eX]

[DOI]

ACM Trans. Graph., 2019

Interpreting Deep Visual Representations via Network Dissection.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2019

The cloud is the limit: A case study of programming on the web, with the web.

[BibT_eX]

[DOI]

David Weintrop

David Bau

Uri Wilensky

Int. J. Child Comput. Interact., 2019

Dissecting Pruned Neural Networks.

[BibT_eX]

[DOI]

Jonathan Frankle

David Bau

CoRR, 2019

Visualizing and Understanding Generative Adversarial Networks (Extended Abstract).

[BibT_eX]

[DOI]

CoRR, 2019

Visualizing and Understanding GANs.

[BibT_eX]

[DOI]

Proceedings of the Deep Generative Models for Highly Structured Data, 2019

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

Seeing What a GAN Cannot Generate.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Learning Words by Drawing Images.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018

Revisiting the Importance of Individual Units in CNNs via Ablation.

[BibT_eX]

[DOI]

CoRR, 2018

Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2018

Interpretable Basis Decomposition for Visual Explanation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2018, 2018

Explaining Explanations: An Overview of Interpretability of Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the 5th IEEE International Conference on Data Science and Advanced Analytics, 2018

2017

Learnable programming: blocks and beyond.

[BibT_eX]

[DOI]

Commun. ACM, 2017

Network Dissection: Quantifying Interpretability of Deep Visual Representations.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2015

Supporting the Computer Science Learning Process.

[BibT_eX]

[DOI]

Proceedings of the 46th ACM Technical Symposium on Computer Science Education, 2015

Using Pencil Code to Bridge the Gap between Visual and Text-Based Coding (Abstract Only).

[BibT_eX]

[DOI]

David Bau

Matthew Dawson

Anthony Bau

Proceedings of the 46th ACM Technical Symposium on Computer Science Education, 2015

Pencil code: block code for a text world.

[BibT_eX]

[DOI]

Proceedings of the 14th International Conference on Interaction Design and Children, 2015

2008

Large scale learning and recognition of faces in web videos.

[BibT_eX]

[DOI]

Proceedings of the 8th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2008), 2008

2001

Solving Alignment Using Elementary Linear Algebra.

[BibT_eX]

[DOI]

Proceedings of the Compiler Optimizations for Scalable Parallel Systems Languages, 2001

1997

Numerical linear algebra.

[BibT_eX]

[DOI]

Lloyd N. Trefethen

David Bau

SIAM, ISBN: 978-0-89871-361-9, 1997

David Bau

Timeline

Legend:

Links

On csauthors.net:

Bibliography

Loading...