-
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
Paper • 2408.13233 • Published • 23 -
Heterogeneous Multi-task Learning with Expert Diversity
Paper • 2106.10595 • Published • 2 -
Residual Mixture of Experts
Paper • 2204.09636 • Published • 1 -
Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition
Paper • 2307.05956 • Published • 1
Hazem Essam
hazemessam
AI & ML interests
Protein Language Modeling and Natural Language Processing
Organizations
-
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
Paper • 2408.13233 • Published • 23 -
Heterogeneous Multi-task Learning with Expert Diversity
Paper • 2106.10595 • Published • 2 -
Residual Mixture of Experts
Paper • 2204.09636 • Published • 1 -
Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition
Paper • 2307.05956 • Published • 1
datasets 35
hazemessam/subcellular-localization
Viewer • Updated • 14k • 7
hazemessam/deeploc-2
Preview • Updated • 12
hazemessam/deeploc-2.1
Preview • Updated • 5
hazemessam/secondary_structure
Viewer • Updated • 10.8k • 17
hazemessam/solubility
Viewer • Updated • 71.4k • 36
hazemessam/beta-lactamase
Viewer • Updated • 5.2k • 57
hazemessam/ml-1m
Preview • Updated • 614
hazemessam/ml-32m
Preview • Updated • 47
hazemessam/food
Viewer • Updated • 711k • 17
hazemessam/ml-25m
Preview • Updated • 44