Publications

USVSN Sai Prashanth, Alvin Deng, Kyle O'Brien, Jyothir S V, Mohammad Aflah Khan, Jaydeep Borkar, Christopher A. Choquette-Choo, Jacob Ray Fuehne, Stella Biderman, Tracy Ke, Katherine Lee, Naomi Saphra (2025). Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon. International Conference on Learning Representations (ICLR).
Cite URL
Oskar Van Der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema, Stella Biderman (2025). PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs. International Conference on Learning Representations (ICLR).
PDF Cite
Michael Y. Hu, Shreyans Jain, Sangam Chaulagain, Naomi Saphra (2025). How to visualize training dynamics in neural networks. Blog Post Track at International Conference on Learning Representations (ICLR BlogPosts).
Cite
Rosie Zhao, Tian Qin, David Alvarez-Melis, Sham Kakade, Naomi Saphra (2025). Distributional Scaling Laws for Emergent Capabilities.
Cite URL
Tian Qin, Naomi Saphra, David Alvarez-Melis (2025). Sometimes I am a Tree: Data drives fragile hierarchical generalization.
Cite URL
Sonja Johnson-Yu, Satpreet Harcharan Singh, Federico Pedraja, Denis Turcu, Pratyusha Sharma, Naomi Saphra, Nathaniel Sawtell, Kanaka Rajan (2024). Understanding biological active sensing behaviors by interpreting learned artificial agent policies. Workshop on Interpretable Policies in Reinforcement Learning @RLC-2024.
Cite URL
Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach (2024). Transcendence: Generative Models Can Outperform The Experts That Train Them. Neural Information Processing Systems (NeurIPS).
Cite URL
Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng (2024). TRAM: Bridging Trust Regions and Sharpness Aware Minimization. International Conference on Learning Representations (ICLR).
Cite URL
Angelica Chen, Ravid Schwartz-Ziv, Kyunghyun Cho, Matthew Leavitt, Naomi Saphra (2024). Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs. International Conference on Learning Representations (ICLR).
Cite URL
Naomi Saphra, Sarah Wiegreffe (2024). Mechanistic?. EMNLP BlackboxNLP Workshop.
Cite URL