by Omid Saremi Papers
4 papers found
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
Vimal Thilak, Chen Huang, Omid Saremi et al.
ICLR 2024spotlight
22
citations
Vanishing Gradients in Reinforcement Finetuning of Language Models
Noam Razin, Hattie Zhou, Omid Saremi et al.
ICLR 2024poster
What Algorithms can Transformers Learn? A Study in Length Generalization
Hattie Zhou, Arwen Bradley, Etai Littwin et al.
ICLR 2024poster
When can transformers reason with abstract symbols?
Enric Boix-Adserà, Omid Saremi, Emmanuel Abbe et al.
ICLR 2024poster