Omid Saremi

20 papers A* 6Journal 12Unranked 2
YearRankTypeTitle / Venue / Authors
2025 J jnl
To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models.
CoRR
Eran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Joshua M. Susskind, Etai Littwin
2024 A* conf
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad.
NeurIPS
Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Colin Sandon, Omid Saremi
2024 J jnl
How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad.
CoRR
Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Colin Sandon, Omid Saremi
2024 A* conf
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks.
NeurIPS
Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua M. Susskind
2024 J jnl
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks.
CoRR
Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua M. Susskind
2024 A* conf
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures.
ICLR
Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
2024 J jnl
The Slingshot Effect: A Late-Stage Optimization Anomaly in Adaptive Gradient Methods.
Trans. Mach. Learn. Res.
Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind
2024 A* conf
Vanishing Gradients in Reinforcement Finetuning of Language Models.
ICLR
Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
2024 A* conf
What Algorithms can Transformers Learn? A Study in Length Generalization.
ICLR
Hattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Joshua M. Susskind, Samy Bengio, Preetum Nakkiran
2024 A* conf
When can transformers reason with abstract symbols?
ICLR
Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua M. Susskind
2023 J jnl
Adaptivity and Modularity for Efficient Generalization Over Task Complexity.
CoRR
Samira Abnar, Omid Saremi, Laurent Dinh, Shantel Wilson, Miguel Ángel Bautista, Chen Huang, Vimal Thilak, Etai Littwin, Jiatao Gu, Josh M. Susskind, Samy Bengio
2023 J jnl
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures.
CoRR
Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
2023 J jnl
Vanishing Gradients in Reinforcement Finetuning of Language Models.
CoRR
Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
2023 J jnl
What Algorithms can Transformers Learn? A Study in Length Generalization.
CoRR
Hattie Zhou, Arwen Bradley, Etai Littwin, Noam Razin, Omid Saremi, Josh M. Susskind, Samy Bengio, Preetum Nakkiran
2023 J jnl
When can transformers reason with abstract symbols?
CoRR
Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe, Samy Bengio, Etai Littwin, Joshua M. Susskind
2022 J jnl
The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon.
CoRR
Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind
2021 J jnl
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks.
CoRR
Etai Littwin, Omid Saremi, Shuangfei Zhai, Vimal Thilak, Hanlin Goh, Joshua M. Susskind, Greg Yang
2021 J jnl
Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks.
CoRR
Shih-Yu Sun, Vimal Thilak, Etai Littwin, Omid Saremi, Joshua M. Susskind
2015 — conf
An Improved Continuous-Action Extended Classifier Systems for Function Approximation.
Complex Adaptive Systems
Omid Saremi, Masoud Shariat Panahi, Amin Sabzehzar
2015 — conf
An Improved eXtended Classifier System for the Real-time-input Real-time-output (XCSRR) Stability Control of a Biped Robot.
Complex Adaptive Systems
Amin Sabzehzar, W. L. Shan, M. Shariat Panahi, Omid Saremi