William Merrill
Scholar

William Merrill

Google Scholar ID: CyjChJQAAAAJ
Ai2 / TTIC
language modelsformal languagescomputational linguisticsdeep learning
Citations & Impact
All-time
Citations
3,916
 
H-index
21
 
i10-index
31
 
Publications
20
 
Co-authors
25
list available
Contact
Resume (English only)
Academic Achievements
  • Dissertation publicly released in 2025
  • Paper 'Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases' at ACL 2025 received Outstanding Paper Award
  • Co-authored 'OLMo: Accelerating the Science of Language Models' at ACL 2024, awarded Best Theme Paper
  • Published numerous papers at top venues including ICLR, ICML, EMNLP, COLM, TACL, ACL, and DLT on topics such as transformer expressivity, semantic learning in language models, and state-space models
  • Key contributions include works like 'Exact Expressive Power of Transformers with Padding', 'A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers', and 'The Expressive Power of Transformers with Chain of Thought'