On the Expressive Power of Transformers for Contextual Relations

arXiv:2603.25860 · stat.ML, cs.LG · Submitted 2026-03-26 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-03-26

Updated: 2026-09-25

Terminology

• Transformer — 83× in this paper · explained in 2 episodes
• Optimal Transport — 23× in this paper · explained in 5 episodes
• Transformer Architecture — 16× in this paper · explained in 2 episodes
• Attention Mechanism — 12× in this paper · explained in 3 episodes
• Wasserstein Distance — 9× in this paper · explained in 4 episodes
• Regularization — 8× in this paper · explained in 3 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Unified Framework — 3× in this paper · explained in 5 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cross-Attention Mechanism — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• Transformers are Universal In-context Learners
• Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
• Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier