Devanshu Agrawal
4 papers · 2020–2024 · 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
(10)
❓
The Questioner
Venues
Top co-authors
Research topics
Deep Learning
(3)
Architectures
(3)
Artificial Intelligence
(2)
Machine Learning
(2)
Optimization & Theory · Machine Learning
(2)
Natural Language Processing
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Core AI
(1)
Generation
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
neural network architecture
(2)
group invariance
(2)
question answering
(1)
prompt engineering
(1)
neural architecture search
(1)
neural architecture
(1)
gaussian process
(1)
3d object classification
(1)
bayesian neural network
(1)
shallow neural network
(1)
retrieval-augmented generation
(1)
cohomology class
(1)
long context
(1)
infinite width
(1)
long-context model
(1)
representation theory
(1)
equivariant network
(1)
in-context retrieval
(1)
kernel methods
(1)
large language model
(1)
Papers
Can’t Remember Details in Long Documents? You Need Some R&R
EMNLP 2024
Densely Connected G-invariant Deep Neural Networks with Signed Permutation Representations
JMLR 2023
A Classification of G-invariant Shallow Neural Networks
NeurIPS 2022
Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
JMLR 2020