Architectures
30,950 papers (33 classified directly here)
Subtopics · a paper can sit in several, so these overlap
Papers per year
2
3
15
13
18
17
27
39
43
74
94
221
536
912
1,611
2,559
3,004
3,504
3,729
4,021
4,550
4,519
1,439
'10
'15
'20
'25
Papers (including subtopics)
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
NeurIPS 2024
On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions
AISTATS 2024
On the Importance of Large Objects in CNN Based Object Detection Algorithms
WACV 2024
On the In-context Generation of Language Models
EMNLP 2024
On the Language Encoder of Contrastive Cross-modal Models
ACL 2024
On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
ICML 2024
On the Nonlinearity of Layer Normalization
ICML 2024
On the Power of Decision Trees in Auto-Regressive Language Modeling
NeurIPS 2024
On the Power of Small-size Graph Neural Networks for Linear Programming
NeurIPS 2024
On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
ICLR 2024
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks
CVPR 2024
On the Role of Attention Masks and LayerNorm in Transformers
NeurIPS 2024
On the Role of Discrete Tokenization in Visual Representation Learning
ICLR 2024
On the Sample Complexity of Two-Layer Networks: Lipschitz Vs. Element-Wise Lipschitz Activation
ALT 2024
On the Scalability of GNNs for Molecular Graphs
NeurIPS 2024
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task
EMNLP 2024
On the Sparsity of the Strong Lottery Ticket Hypothesis
NeurIPS 2024
On the Stability of Expressive Positional Encodings for Graphs
ICLR 2024
On the Surprising Effectiveness of Attention Transfer for Vision Transformers
NeurIPS 2024
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks
AISTATS 2024
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
AISTATS 2024
On the token distance modeling ability of higher RoPE attention dimension
EMNLP 2024
On the Topology Awareness and Generalization Performance of Graph Neural Networks
ECCV 2024
On the Vulnerability of Skip Connections to Model Inversion Attacks
ECCV 2024
On the Way to Lossless Compression of Language Transformers: Exploring Cross-Domain Properties of Quantization
COLING 2024