David So
7 papers · 2019–2023 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Deep Learning
(7)
Architectures
(6)
Machine Learning
(5)
Optimization & Theory · Machine Learning
(4)
Techniques
(4)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Core AI
(2)
Optimization & Theory · Deep Learning
(2)
Application Areas
(1)
Generation
(1)
Learning Paradigms
(1)
Models
(1)
Resources & Methods
(1)
Keywords
neural architecture search
(4)
transformer architecture
(4)
evolutionary algorithm
(3)
language model
(2)
efficient computing
(2)
neural architecture
(1)
gradient descent
(1)
learning algorithm
(1)
scaling law
(1)
sequence model
(1)
weight averaging
(1)
feed-forward network
(1)
evolutionary search
(1)
prompt tuning
(1)
model efficiency
(1)
algorithm discovery
(1)
layer normalization
(1)
gating mechanism
(1)
emergent abilities
(1)
multi-layer perceptron
(1)
Papers
Brainformers: Trading Simplicity for Efficiency
ICML 2023
EvoPrompting: Language Models for Code-Level Neural Architecture Search
NeurIPS 2023
Transcending Scaling Laws with 0.1% Extra Compute
EMNLP 2023
Pay Attention to MLPs
NeurIPS 2021
Searching for Efficient Transformers for Language Modeling
NeurIPS 2021
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
ICML 2020
The Evolved Transformer
ICML 2019