William Held
Scholar

William Held

Google Scholar ID: SP9VJNkAAAAJ
Georgia Tech
Data-Centric MLDomain RobustnessNatural Language ProcessingVery Amazing Research
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,511
 
H-index
13
 
i10-index
15
 
Publications
20
 
Co-authors
14
list available
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
6 items
Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
2026
Cited
0
Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens
2026
Cited
0
Culture Cartography: Mapping the Landscape of Cultural Knowledge
2025
Cited
0
AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation
2025
Cited
0
SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs
2025
Cited
0
Optimizing Pretraining Data Mixtures with LLM-Estimated Utility
2025
Cited
0
Resume (English only)
Academic Achievements
  • No specific information provided.
Research Experience
  • Before that, early engineer at Sunshine.
Education
  • Currently, Machine Learning PhD at Georgia Tech, advised by Diyi Yang in the Stanford NLP Group.
Background
  • Focused on enabling inclusive language technology by modeling linguistic variation.
Miscellany
  • No specific information provided.
Co-authors
14 total
Diyi Yang
Diyi Yang
Stanford University
Caleb Ziems
Caleb Ziems
Stanford University
Omar Shaikh
Omar Shaikh
Stanford University
Michael J. Ryan
Michael J. Ryan
Stanford University
Dan Jurafsky
Dan Jurafsky
Professor of Linguistics and Computer Science, Stanford University
Co-author 6
Co-author 6
Yanzhe Zhang
Yanzhe Zhang
Georgia Institute of Technology
Camille Harris
Camille Harris
Postdoctoral Associate, Cornell Tech University