Scholar
Josh Gardner
Google Scholar ID: SSq1t_YAAAAJ
Anthropic
Citations & Impact
Citations
11,424
H-index
22
i10-index
29
Publications
20
Co-authors
21
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Apple Intelligence Foundation Language Models
- - Language Models Improve When Pretraining Data Matches Target Tasks
- - Large Scale Transfer Learning for Tabular Data via Language Modeling
- - DataComp-LM: In search of the next generation of training sets for language models
- - LLark: A Multimodal Instruction-Following Language Model for Music
- - Benchmarking Distribution Shift in Tabular Data with TableShift
- - VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models
- - Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity
- - Subgroup Robustness Grows on Trees: An Empirical Baseline Study
- - OpenFlamingo: An Open-Source Framework for Training Vision-Language Models with In-Context Learning
- - MT3: Multi-Task Multitrack Music Transcription
- - Evaluating the Fairness of Predictive Student Models Through Slicing Analysis (Best Paper Award)
Research Experience
- - Member of Technical Staff at Anthropic
- - Research Scientist on the Foundation Modeling team at Apple
Education
- - PhD in Computer Science from the University of Washington's Paul G. Allen School of Computer Science & Engineering, advised by Ludwig Schmidt
- - M.S. in Applied Statistics from the University of Michigan
- - M.S. in Information Science from the University of Michigan
- - B.A. with Highest Honors in Philosophy from the University of Michigan
Background
- Research interests include designing controlled experiments to understand artificial intelligence/machine learning models and using insights from these experiments to develop improved models. Particularly interested in the impact of data on machine learning models and how to develop models that can understand new kinds of data or reason across modalities.
