Andrey Gromov - RankMe

23 papers A* 5Journal 17Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs. CoRR Dayal Singh Kalra, Jean-Christophe Gagnon-Audet, Andrey Gromov, Ishita Mediratta, Kelvin Niu, Alexander H. Miller, Michael Shvartsman
2026	J	`jnl`	MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment. CoRR Hanxian Huang, Igor Fedorov, Andrey Gromov, Bernard Beckerman, Naveen Suda, David Eriksson, Maximilian Balandat, Rylan Conway, Patrick Huber, Chinnadhurai Sankar, Ayushi Dalmia, Zechun Liu, Lemeng Wu, Tarek Elgamal, Adithya Sagar, Vikas Chandra, Raghuraman Krishnamoorthi
2026	J	`jnl`	On the origin of neural scaling laws: from random graphs to natural language. CoRR Maissam Barkeshli, Alberto Alfarano, Andrey Gromov
2025	A*	`conf`	PARQ: Piecewise-Affine Regularized Quantization. ICML Lisa Jin, Jianhao Ma, Zechun Liu, Andrey Gromov, Aaron Defazio, Lin Xiao
2025	J	`jnl`	PARQ: Piecewise-Affine Regularized Quantization. CoRR Lisa Jin, Jianhao Ma, Zechun Liu, Andrey Gromov, Aaron Defazio, Lin Xiao
2025	J	`jnl`	Spectral Journey: How Transformers Predict the Shortest Path. CoRR Andrew Cohen, Andrey Gromov, Kaiyu Yang, Yuandong Tian
2025	A*	`conf`	The Unreasonable Ineffectiveness of the Deeper Layers. ICLR Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso, Daniel A. Roberts
2025	J	`jnl`	Towards Distributed Neural Architectures. CoRR Aditya Cowsik, Tianyu He, Andrey Gromov
2024	J	`jnl`	Bridging Associative Memory and Probabilistic Modeling. CoRR Rylan Schaeffer, Nika Zahedi, Mikail Khona, Dhruv Pai, Sang T. Truong, Yilun Du, Mitchell Ostrow, Sarthak Chandra, Andres Carranza, Ila Rani Fiete, Andrey Gromov, Sanmi Koyejo
2024	J	`jnl`	Grokking Modular Polynomials. CoRR Darshil Doshi, Tianyu He, Aritra Das, Andrey Gromov
2024	J	`jnl`	Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data. CoRR Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey, Rafael Rafailov, Henry Sleight, John Hughes, Tomasz Korbak, Rajashree Agrawal, Dhruv Pai, Andrey Gromov, Daniel A. Roberts, Diyi Yang, David L. Donoho, Sanmi Koyejo
2024	A*	`conf`	Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks. NeurIPS Tianyu He, Darshil Doshi, Aritra Das, Andrey Gromov
2024	J	`jnl`	Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks. CoRR Tianyu He, Darshil Doshi, Aritra Das, Andrey Gromov
2024	J	`jnl`	The Unreasonable Ineffectiveness of the Deeper Layers. CoRR Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso, Daniel A. Roberts
2024	A*	`conf`	To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets. ICLR Darshil Doshi, Aritra Das, Tianyu He, Andrey Gromov
2024	J	`jnl`	Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations. CoRR Rylan Schaeffer, Victor Lecomte, Dhruv Bhandarkar Pai, Andres Carranza, Berivan Isik, Alyssa Unell, Mikail Khona, Thomas E. Yerxa, Yann LeCun, SueYeon Chung, Andrey Gromov, Ravid Shwartz-Ziv, Sanmi Koyejo
2023	A*	`conf`	Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications. NeurIPS Darshil Doshi, Tianyu He, Andrey Gromov
2023	J	`jnl`	Deconstructing the generalization gap. Nat. Mac. Intell. Andrey Gromov
2023	J	`jnl`	Grokking modular arithmetic. CoRR Andrey Gromov
2023	J	`jnl`	To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets. CoRR Darshil Doshi, Aritra Das, Tianyu He, Andrey Gromov
2022	J	`jnl`	AutoInit: Automatic Initialization via Jacobian Tuning. CoRR Tianyu He, Darshil Doshi, Andrey Gromov
2021	J	`jnl`	Critical initialization of wide and deep neural networks through partial Jacobians: general theory and applications to LayerNorm. CoRR Darshil Doshi, Tianyu He, Andrey Gromov
2014	—	`conf`	The Concept of Automation in Conventional Systems Creation Applied to the Preliminary Aircraft Design. ACS Nikolay Borgest, Maksim Korovin, Andrey Gromov, Aleksey Gromov