Naomi Saphra
23 papers · 2014–2025 · 8 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 14 separate collaboration groups - the largest holds only 30% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Naomi Saphra?
3 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Adam Lopez, Kyunghyun Cho, Jeevesh Juneja
7 papers
· 2015–2024
· NAACL, ICLR, EMNLP
Hide ▲
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
NAACL 2024
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
ICLR 2024
Linear Connectivity Reveals Generalization Strategies
ICLR 2023
LSTMs Compose—and Learn—Bottom-Up
EMNLP 2020
Understanding Learning Dynamics Of Language Models with SVCCA
NAACL 2019
Language Models Learn POS First
EMNLP 2018
AMRICA: an AMR Inspector for Cross-language Alignments
NAACL 2015
11 papers whose co-authors appear nowhere else under this name
Data Drives Unstable Hierarchical Generalization in LMs
EMNLP 2025
Using Shapley interactions to understand how models use structure
ACL 2025
Attribute Diversity Determines the Systematicity Gap in VQA
EMNLP 2024
ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Context
EMNLP 2024
Dynamic Masking Rate Schedules for MLM Pretraining
EACL 2024
Fast Forwarding Low-Rank Training
EMNLP 2024
Mechanistic?
EMNLP 2024
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
ICLR 2024
Transcendence: Generative Models Can Outperform The Experts That Train Them
NeurIPS 2024
The MultiBERTs: BERT Reproductions for Robustness Analysis
ICLR 2022
Understanding Objects in Detail with Fine-Grained Attributes
CVPR 2014