Martin Wattenberg

Social Sciences · Social Sciences

64h-index32.2kcitations248works3.12yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Electoral Systems and Political Participation(56), Data Visualization and Analytics(52), Topic Modeling(23), Social Media and Politics(19), Natural Language Processing Techniques(15)

Publications247 total

Decomposing Query-Key Feature Interactions Using Contrastive Covariances
arXiv (Cornell University)·2026Open Access
Decomposing Query-Key Feature Interactions Using Contrastive Covariances
ArXiv.org·2026Open Access
Does visualization help AI understand data?
2025
Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
2025
Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
arXiv (Cornell University)·2025· 3 citedOpen Access
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
arXiv (Cornell University)·2025Open Access
Chronotome: Real-Time Topic Modeling for Streaming Embedding Spaces
arXiv (Cornell University)·2025Open Access
400 V SiC MOSFET Technology Empowering Innovative Three-Level Power Supplies for AI Servers
2025
Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
arXiv (Cornell University)·2025Open Access
Story Ribbons: Reimagining Storyline Visualizations with Large Language Models
arXiv (Cornell University)·2025Open Access
Does visualization help AI understand data?
arXiv (Cornell University)·2025· 1 citedOpen Access
Can Interpretation Predict Behavior on Unseen Data?
arXiv (Cornell University)·2025Open Access
400V SiC MOSFET empowering three-level topologies for highly efficient applications from motor-drives to AI
Power Electronic Devices and Components·2025· 1 citedOpen Access
400 V SiC MOSFET empowering three-level topologies for highly efficient applications from motor-drives to AI
HAL (Le Centre pour la Communication Scientifique Directe)·2025Open Access
When Bad Data Leads to Good Models
arXiv (Cornell University)·2025Open Access
A High-Efficiency 5.5kW Battery Backup Unit for OCP Open Rack V3 Using Partial Power Conversion
SPIRE - Sciences Po Institutional REpository·2025Open Access
Shared Global and Local Geometry of Language Model Embeddings
arXiv (Cornell University)·2025Open Access
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
arXiv (Cornell University)·2025Open Access
Open Problems in Mechanistic Interpretability
arXiv (Cornell University)·2025· 5 citedOpen Access
ICLR: In-Context Learning of Representations
arXiv (Cornell University)·2024· 1 citedOpen Access
page 1 of 13Next →

Frequent Co-authors

Fernanda Viégas(28), Nikhil Thorat(6), Been Kim(6), Daniel Smilkov(5), Greg S. Corrado(4), James Wexler(4), Emily Reif(4), Zhifeng Chen(3), Jay B. Dean(3), Mike Schuster(3), Carrie J. Cai(3), Frank van Ham(3), Ann Yuan(3), Rajat Monga(2), Melvin Johnson(2), Quoc V. Le(2), Maxim Krikun(2), Yonghui Wu(2), Macduff Hughes(2), D. Sculley(2)