Levi, Noam Itzhak

13 publications

ICLR 2026 Learning Shrinks the Hard Tail: Training‑Dependent Inference Scaling in a Solvable Linear Model Noam Itzhak Levi

ICLR 2026 Pretraining Scaling Laws for Generative Evaluations of Language Models Rylan Schaeffer, Noam Itzhak Levi, Brando Miranda, Sanmi Koyejo

ICML 2025 A Simple Model of Inference Scaling Laws Noam Itzhak Levi

ICLRW 2025 A Simple Model of Inference Scaling Laws Noam Itzhak Levi

NeurIPS 2025 Ascent Fails to Forget Ioannis Mavrothalassitis, Pol Puigdemont, Noam Itzhak Levi, Volkan Cevher

ICML 2025 Grokking at the Edge of Linear Separability Alon Beck, Noam Itzhak Levi, Yohai Bar-Sinai

ICLR 2025 Probing the Latent Hierarchical Structure of Data via Diffusion Models Antonio Sclocchi, Alessandro Favero, Noam Itzhak Levi, Matthieu Wyart

ICML 2025 The Underlying Universal Statistical Structure of Natural Datasets Noam Itzhak Levi, Yaron Oz

ICLR 2024 Grokking in Linear Estimators -- a Solvable Model That Groks Without Understanding Noam Itzhak Levi, Alon Beck, Yohai Bar-Sinai

NeurIPSW 2024 Unraveling the Latent Hierarchical Structure of Language and Images via Diffusion Models Antonio Sclocchi, Noam Itzhak Levi, Alessandro Favero, Matthieu Wyart

NeurIPSW 2024 Unraveling the Latent Hierarchical Structure of Language and Images via Diffusion Models Antonio Sclocchi, Noam Itzhak Levi, Alessandro Favero, Matthieu Wyart

ICLR 2023 Noise Injection Node Regularization for Robust Learning Noam Itzhak Levi, Itay Mimouni Bloch, Marat Freytsis, Tomer Volansky

ICLRW 2023 Noise Injection as a Probe of Deep Learning Dynamics Noam Itzhak Levi, Itay Mimouni Bloch, Marat Freytsis, Tomer Volansky