David Bau
34 papers · 2017–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+15 more ↓ Show less ↑
🏃 Academic Marathon (9) 🌍 Conference Polyglot (10) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (8)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(8)
🌍
Conference Polyglot
(10)
👥
Mega-Team
(23)
🤝
Dynamic Duo
(13)
🔬
Deep Specialist
(10)
🧬
Topic Evolution
🏆
Keyword Champion
(2)
❓
The Questioner
📈
Trend Setter
🗃️
Keyword Collector
(95)
🔥
Unstoppable
(10)
⚡
Prolific Year
(7)
💎
Century Club
(34)
🚀
Conference Pioneer
Conferences
ICLR (9)
ICCV (5)
CVPR (4)
ECCV (4)
NIPS (4)
EMNLP (3)
WACV (2)
ACL (1)
CONLL (1)
ICML (1)
Top co-authors
Keywords
language model
(5)
generative adversarial network
(4)
diffusion model
(4)
causal intervention
(3)
image generation
(3)
large language model
(2)
latent space
(2)
token prediction
(2)
language model interpretability
(2)
model editing
(2)
mechanistic interpretability
(2)
representation learning
(2)
mode collapse
(2)
image synthesis
(1)
feature embedding
(1)
visual processing
(1)
content moderation
(1)
named entity recognition
(1)
feature extraction
(1)
semantic segmentation
(1)
Papers
Distilling Diversity and Control in Diffusion Models
WACV 2026
MIB: A Mechanistic Interpretability Benchmark
ICML 2025
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
ICLR 2025
Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
EMNLP 2025
Position-aware Automatic Circuit Discovery
ACL 2025
NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals
ICLR 2025
SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
ICCV 2025
Linearity of Relation Decoding in Transformer Language Models
ICLR 2024
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
NIPS 2024
Unified Concept Editing in Diffusion Models
WACV 2024
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
ICLR 2024
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models
ECCV 2024
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
EMNLP 2024
Function Vectors in Large Language Models
ICLR 2024
Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
EMNLP 2023
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
ICLR 2023
Mass-Editing Memory in a Transformer
ICLR 2023
Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
CONLL 2023
FIND: A Function Description Benchmark for Evaluating Interpretability Methods
NIPS 2023
Erasing Concepts from Diffusion Models
ICCV 2023
Natural Language Descriptions of Deep Visual Features
ICLR 2022
Locating and Editing Factual Associations in GPT
NIPS 2022
Disentangling Visual and Written Concepts in CLIP
CVPR 2022
Editing a classifier by rewriting its prediction rules
NIPS 2021
Sketch Your Own GAN
ICCV 2021
Toward a Visual Concept Vocabulary for GAN Latent Space
ICCV 2021
What makes fake images detectable? Understanding properties that generalize
ECCV 2020
Rewriting a Deep Generative Model
ECCV 2020
Diverse Image Generation via Self-Conditioned GANs
CVPR 2020
Learning Words by Drawing Images
CVPR 2019
Seeing What a GAN Cannot Generate
ICCV 2019
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
ICLR 2019
Interpretable Basis Decomposition for Visual Explanation
ECCV 2018
Network Dissection: Quantifying Interpretability of Deep Visual Representations
CVPR 2017