MW
Martin Wattenberg
cs.LGcs.AIcs.CLcs.HCstat.MLcs.CVComputer GraphicsUser-Computer Interfacecs.CYSoftware
On Valency
published · living versionsW_snpkpxfk·v1 · currentpublished
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
with Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo +35
1 version
Preprints & journals
60 papers in the corpus · 2006–2026Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics2508.11017v4 · Carter Blum, Katja Filippova, Ann Yuan et al.2025 · 2 citationsarXiv
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types2604.09544v3 · Hadas Orgad, Boyi Wei, Kaden Zheng et al.2026 · 0 citationsarXiv
Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry2510.08638v3 · Thomas Fel, Binxu Wang, Michael A. Lepori et al.2025 · 5 citationsICLR 2024
Decomposing Query-Key Feature Interactions Using Contrastive Covariances2602.04752v1 · Andrew Lee, Yonatan Belinkov, Fernanda Vi'egas et al.2026 · 0 citationsarXiv
Story Ribbons: Reimagining Storyline Visualizations with Large Language Models.41343311 · Yeh, Catherine, Menon, Tara, Arya, Robin Singh et al.2025 · 1 citationIEEE transactions on visualization and computer graphics. 2025;PP
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls2510.00184v1 · Xiaoyan Bai, Itamar Pres, Yuntian Deng et al.2025 · 0 citationsarXiv
Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces2509.01051v1 · Matte Lim, Catherine Yeh, Martin Wattenberg et al.2025 · 0 citationsarXiv
Story Ribbons: Reimagining Storyline Visualizations with Large Language Models2508.06772v1 · Catherine Yeh, Tara Menon, Robin Singh Arya et al.2025 · 1 citationarXiv
Does visualization help AI understand data?2507.18022v1 · Victoria R. Li, Johnathan Sun, Martin Wattenberg2025 · 2 citationsarXiv
Shared Global and Local Geometry of Language Model Embeddings2503.21073v3 · Andrew Lee, Melanie Weber, Fernanda Vi'egas et al.2025 · 0 citationsarXiv
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models2502.12892v2 · Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince et al.2025 · 1 citationProceedings of the 42nd International Conference on Machine Learning (ICML), 2025
When Bad Data Leads to Good Models2505.04741v1 · Kenneth Li, Yida Chen, Fernanda Vi'egas et al.2025 · 0 citationsarXiv
ICLR: In-Context Learning of Representations2501.00070v2 · Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana et al.2024 · 1 citationInternational Conference on Learning Representations, 2025
Open Problems in Mechanistic Interpretability2501.16496v1 · Lee Sharkey, Bilal Chughtai, Joshua Batson et al.2025 · 11 citationsarXiv
Designing a Dashboard for Transparency and Control of Conversational AI2406.07882v3 · Yida Chen, Aoyu Wu, Trevor DePodesta et al.2024 · 1 citationarXiv
Interactive AI Alignment: Specification, Process, and Evaluation Alignment2311.00710v2 · Michael Terry, Chinmay Kulkarni, Martin Wattenberg et al.2023 · 21 citationsarXiv
Relational Composition in Neural Networks: A Survey and Call to Action2407.14662v1 · Martin Wattenberg, Fernanda B. Vi'egas2024 · 1 citationarXiv
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task2210.13382v5 · Kenneth Li, Aspen K. Hopkins, David Bau et al.2022 · 62 citationsarXiv
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model2306.03341v6 · Kenneth Li, Oam Patel, Fernanda Vi'egas et al.2023 · 95 citationsarXiv
Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner2406.11978v1 · Kenneth Li, Yiming Wang, Fernanda Vi'egas et al.2024 · 0 citationsarXiv
Q-Probe: A Lightweight Approach to Reward Maximization for Language Models2402.14688v2 · Kenneth Li, Samy Jelassi, Hugh Zhang et al.2024 · 0 citationsarXiv
ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing2309.09128v3 · Ian Arawjo, Chelse Swoopes, Priyan Vaithilingam et al.2023 · 139 citationsarXiv
Linearity of Relation Decoding in Transformer Language Models2308.09124v2 · Evan Hernandez, Arnab Sen Sharma, Tal Haklay et al.2023 · 3 citationsarXiv
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity2401.01967v1 · Andrew Lee, Xiaoyan Bai, Itamar Pres et al.2024 · 4 citationsarXiv
AttentionViz: A Global View of Transformer Attention.37883259 · Yeh, Catherine, Chen, Yida, Wu, Aoyu et al.2023 · 79 citationsIEEE transactions on visualization and computer graphics. 2024;30(1):262-272
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model2306.05720v2 · Yida Chen, Fernanda Vi'egas, Martin Wattenberg2023 · 4 citationsarXiv
Grand Challenges in Visual Analytics Applications.37713213 · Wu, Aoyu, Deng, Dazhen, Chen, Min et al.2023 · 10 citationsIEEE computer graphics and applications. 2023;43(5):83-90
Emergent Linear Representations in World Models of Self-Supervised Sequence Models2309.00941v2 · Neel Nanda, Andrew Lee, Martin Wattenberg2023 · 35 citationsarXiv
AttentionViz: A Global View of Transformer Attention2305.03210v2 · Catherine Yeh, Yida Chen, Aoyu Wu et al.2023 · 79 citationsarXiv
The System Model and the User Model: Exploring AI Dashboard Design2305.02469v1 · Fernanda Vi'egas, Martin Wattenberg2023 · 1 citationarXiv
Investigating How Practitioners Use Human-AI Guidelines: A Case Study on the People + AI Guidebook2301.12243v2 · Nur Yildirim, Mahima Pushkarna, Nitesh Goyal et al.2023 · 103 citationsProceedings of the 2023 CHI Conference on Human Factors in Computing Systems
Acquisition of chess knowledge in AlphaZero.36375061 · McGrath, Thomas, Kapishnikov, Andrei, Tomašev, Nenad et al.2022 · 103 citationsProceedings of the National Academy of Sciences of the United States of America. 2022;119(47):e2206625119
Toy Models of Superposition2209.10652v1 · Nelson Elhage, Tristan Hume, Catherine Olsson et al.2022 · 49 citationsarXiv
Interpreting a Machine Learning Model for Detecting Gravitational Waves2202.07399v1 · Mohammadtaher Safarzadeh, Asad Khan, E. A. Huerta et al.2022 · 0 citationsarXiv
An Interpretability Illusion for BERT2104.07143v1 · Tolga Bolukbasi, Adam Pearce, Ann Yuan et al.2021 · 11 citationsarXiv
"A cold, technical decision-maker": Can AI provide explainability, negotiability, and humanity?2012.00874v1 · Allison Woodruff, Yasmin Asare Anderson, Katherine Jameson Armstrong et al.2020 · 0 citationsarXiv
Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure1903.01069v4 · Been Kim, Emily Reif, Martin Wattenberg et al.2019 · 43 citationsarXiv
Visualizing and Measuring the Geometry of BERT1906.02715v2 · Andy Coenen, Emily Reif, Ann Yuan et al.2019 · 281 citationsarXiv
The What-If Tool: Interactive Probing of Machine Learning Models1907.04135v2 · James Wexler, Mahima Pushkarna, Tolga Bolukbasi et al.2019 · 527 citationsarXiv
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)1711.11279v5 · Been Kim, Martin Wattenberg, Justin Gilmer et al.2017 · 1,076 citationsICML 2018
Deep learning of aftershock patterns following large earthquakes.30158606 · DeVries, Phoebe M R, Viégas, Fernanda, Wattenberg, Martin et al.2019 · 353 citationsNature. 2018;560(7720):632-634
TensorFlow.js: Machine Learning for the Web and Beyond1901.05350v2 · Daniel Smilkov, Nikhil Thorat, Yannick Assogba et al.2019 · 138 citationsarXiv
Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making1902.02960v1 · Carrie J. Cai, Emily Reif, Narayan Hegde et al.2019 · 405 citationsarXiv
Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow.28866562 · Wongsuphasawat, Kanit, Smilkov, Daniel, Wexler, James et al.2018 · 337 citationsIEEE transactions on visualization and computer graphics. 2018;24(1):1-12
Adversarial Spheres1801.02774v3 · Justin Gilmer, Luke Metz, Fartash Faghri et al.2018 · 42 citationsarXiv
GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation1809.01587v1 · Minsuk Kahng, Nikhil Thorat, Duen Horng Chau et al.2018 · 217 citationsarXiv
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation1611.04558v2 · Melvin Johnson, Mike Schuster, Quoc V. Le et al.2016 · 1,873 citationsarXiv
Direct-Manipulation Visualization of Deep Networks1708.03788v1 · Daniel Smilkov, Shan Carter, D. Sculley et al.2017 · 84 citationsarXiv
SmoothGrad: removing noise by adding noise1706.03825v1 · Daniel Smilkov, Nikhil Thorat, Been Kim et al.2017 · 727 citationsarXiv
Embedding Projector: Interactive Visualization and Interpretation of Embeddings1611.05469v1 · Daniel Smilkov, Nikhil Thorat, Charles Nicholson et al.2016 · 154 citationsarXiv
Career total: 221 works. 60 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.