Omid Saremi

1. What Algorithms can Transformers Learn? A Study in Length Generalization
   2023/10/24 by Hattie Zhou, Zhou, Hattie, Arwen Bradley +13 · 2 voices · 21 citations
   Computer Science · #cs.LG #cs.AI #cs.CL #stat.ML
2. When can transformers reason with abstract symbols?
   2023/10/15 by Enric Boix-Adserà, Enric Boix-Adsera, Boix-Adsera, Enric +12 · 1 voice · 4 citations
   Computer Science · #Advanced Text Analysis Techniques #Natural Language Processing Techniques #cs.AI #cs.CL #cs.LG
3. LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
   2023/12/07 by Vimal Thilak, Thilak, Vimal, Chen Huang +13 · 9 citations
   Computer Science · #Face and Expression Recognition #Machine Learning and Data Classification #Anomaly Detection Techniques and Applications
4. How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
   2024/06/10 by Emmanuel Abbe, Emmanuel Abbé, Abbe, Emmanuel +8 · 1 voice · 2 citations
   Computer Science · Psychology · #Computability, Logic, AI Algorithms #Deception detection and forensic psychology #Neural Networks and Applications #cs.AI #cs.LG #stat.ML
5. Vanishing Gradients in Reinforcement Finetuning of Language Models
   2023/10/31 by Noam Razin, Hattie Zhou, Razin, Noam +13 · 6 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Reinforcement Learning in Robotics #Topic Modeling
6. How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
   2024/07/03 by Etai Littwin, Omid Saremi, Littwin, Etai +12 · 1 voice · 5 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #cs.LG
7. Adaptivity and Modularity for Efficient Generalization Over Task Complexity
   2023/10/13 by Samira Abnar, Omid Saremi, Abnar, Samira +19 · 1 citation
   Computer Science · #Machine Learning and Data Classification #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications