Tucker Bottleneck Attention for Multi-Dimensional Sequence Modeling
cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
- Longformer: The Long-Document Transformer
- Generating Long Sequences with Sparse Transformers
- Axial Attention in Multidimensional Transformers
- Tucker Attention: A generalization of approximate attention mechanisms
- BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression
- The Origins of Representation Manifolds in Large Language Models
- Scalable-Softmax Is Superior for Attention
- Higher-Order Transformers With Kronecker-Structured Attention
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- Linformer: Self-Attention with Linear Complexity
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks