Naomi Saphra
23 papers · 2014–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🏃 Academic Marathon (11) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🐝 Cross-Pollinator (13)
🗺️
Taxonomy Completionist
(46)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
⚡
Prolific Year
(9)
🗃️
Keyword Collector
(91)
🔥
Unstoppable
(8)
💎
Century Club
(23)
❓
The Questioner
Conferences
EMNLP (8)
ICLR (6)
NAACL (4)
ACL (1)
COLING (1)
CVPR (1)
EACL (1)
NIPS (1)
Top co-authors
Keywords
language model
(6)
representation learning
(4)
neural network
(3)
syntactic structure
(3)
contextual representation
(2)
part-of-speech tagging
(2)
n-gram model
(2)
model interpretability
(2)
large language model
(2)
learning dynamics
(2)
machine translation
(1)
neural network optimization
(1)
out-of-distribution generalization
(1)
feature attribution
(1)
visual question answering
(1)
neural network training
(1)
performance evaluation
(1)
responsible ai
(1)
imitation learning
(1)
part detection
(1)
Papers
Using Shapley interactions to understand how models use structure
ACL 2025
Data Drives Unstable Hierarchical Generalization in LMs
EMNLP 2025
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
ICLR 2025
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
ICLR 2025
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
NAACL 2024
Dynamic Masking Rate Schedules for MLM Pretraining
EACL 2024
ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Context
EMNLP 2024
Fast Forwarding Low-Rank Training
EMNLP 2024
Attribute Diversity Determines the Systematicity Gap in VQA
EMNLP 2024
Mechanistic?
EMNLP 2024
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
ICLR 2024
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
ICLR 2024
Transcendence: Generative Models Can Outperform The Experts That Train Them
NIPS 2024
Linear Connectivity Reveals Generalization Strategies
ICLR 2023
The MultiBERTs: BERT Reproductions for Robustness Analysis
ICLR 2022
Benchmarking Compositionality with Formal Languages
COLING 2022
A Non-Linear Structural Probe
NAACL 2021
LSTMs Compose—and Learn—Bottom-Up
EMNLP 2020
Pareto Probing: Trading Off Accuracy for Complexity
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
Understanding Objects in Detail with Fine-Grained Attributes
CVPR 2014