Scholar
Samy Jelassi
Google Scholar ID: jq__G-AAAAAJ
Harvard University
Citations & Impact
Citations
975
H-index
16
i10-index
17
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- - Mixture of Parrots: Experts improve memorization more than reasoning
- - Repeat after me: Transformers are better than state space models at copying, 41st International Conference on Machine Learning (ICML), 2024
- - Universal Length Generalization with Turing Programs, In submission
Research Experience
- - Research Fellow at the Center of Mathematical Sciences and Applications (CMSA) at Harvard University
- - Hosts: Boaz Barak and Sham Kakade
- - Interned at Facebook AI Research, Google Deepmind, and Google Research
Education
- - Ph.D., Princeton University, Advisor: Boris Hanin
- - Undergraduate, Ecole Normale Superieure de Lyon, France
Background
- - Research Interests: Creation and optimization of large language models, length generalization problems
- - Professional Field: Implicit bias induced by optimization algorithms and architectural choices
