Saphra, Naomi

17 publications

ICLR 2025 PolyPythias: Stability and Outliers Across Fifty Language Model Pre-Training Runs Oskar van der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema, Stella Biderman

ICLR 2025 Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon USVSN Sai Prashanth, Alvin Deng, Kyle O'Brien, S V Jyothir, Mohammad Aflah Khan, Jaydeep Borkar, Christopher A. Choquette-Choo, Jacob Ray Fuehne, Stella Biderman, Tracy Ke, Katherine Lee, Naomi Saphra

NeurIPSW 2024 Causation Does Not Imply Correlation: A Study of Circuit Mechanisms and Model Behaviors Jenny Kaufmann, Victoria R Li, Martin Wattenberg, David Alvarez-Melis, Naomi Saphra

NeurIPSW 2024 Distributional Scaling Laws for Emergent Capabilities Rosie Zhao, Naomi Saphra, Sham M. Kakade

ICMLW 2024 Loss in the Crowd: Hidden Breakthroughs in Language Model Training Sara Kangaslahti, Elan Rosenfeld, Naomi Saphra

NeurIPSW 2024 Sometimes I Am a Tree: Data Drives Fragile Hierarchical Generalization Tian Qin, Naomi Saphra, David Alvarez-Melis

NeurIPSW 2024 Sometimes I Am a Tree: Data Drives Fragile Hierarchical Generalization Tian Qin, Naomi Saphra, David Alvarez-Melis

ICLR 2024 Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L Leavitt, Naomi Saphra

ICLR 2024 TRAM: Bridging Trust Regions and Sharpness Aware Minimization Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng

NeurIPS 2024 Transcendence: Generative Models Can Outperform the Experts That Train Them Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham Kakade, Eran Malach

NeurIPSW 2024 Twin Studies of Factors in OOD Generalization Victoria R Li, Jenny Kaufmann, David Alvarez-Melis, Naomi Saphra

TMLR 2023 Latent State Models of Training Dynamics Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho

ICLR 2023 Linear Connectivity Reveals Generalization Strategies Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra

ICMLW 2022 Linear Connectivity Reveals Generalization Strategies Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra

ICLR 2022 The MultiBERTs: BERT Reproductions for Robustness Analysis Thibault Sellam, Steve Yadlowsky, Ian Tenney, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Raluca Turc, Jacob Eisenstein, Dipanjan Das, Ellie Pavlick

ICMLW 2019 Sparsity Emerges Naturally in Neural Language Models Naomi Saphra, Adam Lopez

CVPR 2014 Understanding Objects in Detail with Fine-Grained Attributes Andrea Vedaldi, Siddharth Mahendran, Stavros Tsogkas, Subhransu Maji, Ross Girshick, Juho Kannala, Esa Rahtu, Iasonas Kokkinos, Matthew B. Blaschko, David Weiss, Ben Taskar, Karen Simonyan, Naomi Saphra, Sammy Mohamed