Omid Saremi
6 papers · 2024–2024 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (2) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (13) π§ Keyword Pioneer π Cross-Pollinator (12)
β‘
Prolific Year
(6)
β
The Questioner
(3)
Conferences
ICLR (4)
NIPS (2)
Top co-authors
Papers
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
NIPS 2024
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
NIPS 2024
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
ICLR 2024
What Algorithms can Transformers Learn? A Study in Length Generalization
ICLR 2024
Vanishing Gradients in Reinforcement Finetuning of Language Models
ICLR 2024
When can transformers reason with abstract symbols?
ICLR 2024