No article text was recorded for this version.
pairwise attention bottleneck
Version 1 of 120 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Representational Strengths and Limitations of Transformers
- Blog: How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
- Blog: A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
- Blog: Strassen Attention, Split VC Dimension and Compositionality in Transformers
- Blog: Logic and the 2-Simplicial Transformer
- Blog: Context Aware Sequence Modeling
- Blog: On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach
- Blog: Understanding Composition of Word Embeddings via Tensor Decomposition
- Blog: Improving Interpretability via Explicit Word Interaction Graph Layer
- Blog: Jump Self-attention: Capturing High-order Statistics in Transformers
- Blog: Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion
- Blog: Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields
- Blog: Using k-Way Co-Occurrences for Learning Word Embeddings
- Blog: Attention-Based Convolutional Neural Networks for Sentence Classification
- Blog: MuSeM: Detecting Incongruent News Headlines using Mutual Attentive Semantic Matching
- Blog: Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction
- Blog: GNEG: Graph-Based Negative Sampling for word2vec
- Blog: Poly-attention: a general scheme for higher-order self-attention
- Blog: Coordination Among Neural Modules Through a Shared Global Workspace
- Blog: Higher Order Transformers: Efficient Attention Mechanism for Tensor Structured Data
History & citation
Current · Permanent link
- This direction split from Higher-Order Attention for Compositional Reasoning (65% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_pairwise_attention_bottleneck_ec3a44e3,
title = {pairwise attention bottleneck},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pairwise-attention-bottleneck/rdr_ec3a44e332e34079abf96ecf3ca01595},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_pairwise_attention_bottleneck_ec3a44e3_v1,
title = {pairwise attention bottleneck},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pairwise-attention-bottleneck/rdr_ec3a44e332e34079abf96ecf3ca01595/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}