b'David Bau'

research

∙ 09/07/2023

A Function Interpretation Benchmark for Evaluating Interpretability Methods

Labeling neural network submodules with human-legible descriptions is us...

0 Sarah Schwettmann, et al. ∙

research

∙ 08/25/2023

Unified Concept Editing in Diffusion Models

Text-to-image models suffer from various safety issues that may limit th...

0 Rohit Gandikota, et al. ∙

research

∙ 08/17/2023

Linearity of Relation Decoding in Transformer Language Models

Much of the knowledge encoded in transformer language models (LMs) may b...

0 Evan Hernandez, et al. ∙

research

∙ 07/07/2023

Discovering Variable Binding Circuitry with Desiderata

Recent work has shown that computation in language models may be human-u...

0 Xander Davies, et al. ∙

research

∙ 03/13/2023

Erasing Concepts from Diffusion Models

Motivated by recent advancements in text-to-image diffusion, we study er...

0 Rohit Gandikota, et al. ∙

research

∙ 10/24/2022

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

Language models show a surprising range of capabilities, but the source ...

0 Kenneth Li, et al. ∙

research

∙ 10/13/2022

Mass-Editing Memory in a Transformer

Recent work has shown exciting promise in updating large language models...

0 Kevin Meng, et al. ∙

research

∙ 10/06/2022

Content-Based Search for Deep Generative Models

The growing proliferation of pretrained generative models has made it in...

40 Daohan Lu, et al. ∙

research

∙ 07/28/2022

Rewriting Geometric Rules of a GAN

Deep generative models make visual content creation more accessible to n...

39 Sheng-Yu Wang, et al. ∙

research

∙ 07/06/2022

Local Relighting of Real Scenes

We introduce the task of local relighting, which changes a photograph of...

0 Audrey Cui, et al. ∙

research

∙ 06/15/2022

Disentangling visual and written concepts in CLIP

The CLIP network measures the similarity between natural text and images...

8 Joanna Materzyńska, et al. ∙

research

∙ 02/10/2022

Locating and Editing Factual Knowledge in GPT

We investigate the mechanisms underlying factual knowledge recall in aut...

8 Kevin Meng, et al. ∙

research

∙ 01/26/2022

Natural Language Descriptions of Deep Visual Features

Some neurons in deep networks specialize in recognizing highly specific ...

2 Evan Hernandez, et al. ∙

research

∙ 12/02/2021

Editing a classifier by rewriting its prediction rules

We present a methodology for modifying the behavior of a classifier by d...

13 Shibani Santurkar, et al. ∙

research

∙ 10/08/2021

Toward a Visual Concept Vocabulary for GAN Latent Space

A large body of recent work has identified transformations in the latent...

11 Sarah Schwettmann, et al. ∙

research

∙ 08/05/2021

Sketch Your Own GAN

Can a user create a deep generative model by sketching a single example?...

14 Sheng-Yu Wang, et al. ∙

research

∙ 03/19/2021

Paint by Word

We investigate the problem of zero-shot semantic image painting. Instead...

6 David Bau, et al. ∙

research

∙ 09/10/2020

Understanding the Role of Individual Units in a Deep Neural Network

Deep neural networks excel at finding hierarchical representations that ...

11 David Bau, et al. ∙

research

∙ 08/24/2020

What makes fake images detectable? Understanding properties that generalize

The quality of image generation and manipulation is reaching impressive ...

41 Lucy Chai, et al. ∙

research

∙ 07/30/2020

Rewriting a Deep Generative Model

A deep generative model such as a GAN learns to model a rich set of sema...

12 David Bau, et al. ∙

research

∙ 06/18/2020

Diverse Image Generation via Self-Conditioned GANs

We introduce a simple but effective unsupervised method for generating r...

12 Steven Liu, et al. ∙

research

∙ 05/15/2020

Semantic Photo Manipulation with a Generative Image Prior

Despite the recent success of GANs in synthesizing images conditioned on...

21 David Bau, et al. ∙

research

∙ 10/24/2019

Seeing What a GAN Cannot Generate

Despite the success of Generative Adversarial Networks (GANs), mode coll...

53 David Bau, et al. ∙

research

∙ 06/29/2019

Dissecting Pruned Neural Networks

Pruning is a standard technique for removing unnecessary structure from ...

0 Jonathan Frankle, et al. ∙

research

∙ 01/29/2019

Visualizing and Understanding Generative Adversarial Networks (Extended Abstract)

Generative Adversarial Networks (GANs) have achieved impressive results ...

22 David Bau, et al. ∙

research

∙ 11/26/2018

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Generative Adversarial Networks (GANs) have recently achieved impressive...

10 David Bau, et al. ∙

research

∙ 06/07/2018

Revisiting the Importance of Individual Units in CNNs via Ablation

We revisit the importance of the individual units in Convolutional Neura...

0 Bolei Zhou, et al. ∙

research

∙ 05/31/2018

Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning

There has recently been a surge of work in explanatory artificial intell...

0 Leilani H. Gilpin, et al. ∙

research

∙ 11/15/2017

Interpreting Deep Visual Representations via Network Dissection

The success of recent deep convolutional neural networks (CNNs) depends ...

0 Bolei Zhou, et al. ∙

research

∙ 05/26/2017

Learnable Programming: Blocks and Beyond

Blocks-based programming has become the lingua franca for introductory c...

0 David Bau, et al. ∙

research

∙ 04/19/2017

Network Dissection: Quantifying Interpretability of Deep Visual Representations

We propose a general framework called Network Dissection for quantifying...

0 David Bau, et al. ∙

David Bau

Featured Co-authors