Attention-based representations for multi-task computation
cs.LG, cs.AI, cs.CC
Submitted: 2026-08-04
Updated: 2026-08-04
Terminology
Sources
- Theoretical limitations of multi-layer Transformer
- Tighter Bounds on the Expressivity of Transformer Encoders
- Few-Shot Learning via Learning the Representation, Provably
- Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
- Lower bounds on transformers with infinite precision
- Parity, Sensitivity, and Transformers
- A Structured Self-attentive Sentence Embedding
- Transformers Learn Shortcuts to Automata
- The Parallelism Tradeoff: Limitations of Log-Precision Transformers
- A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
- On Limitations of the Transformer Architecture
- Representational Strengths and Limitations of Transformers
- One-layer transformers fail to solve the induction heads task
- Transformers, parallel computation, and logarithmic depth
- Provable Meta-Learning of Linear Representations
- The Effect of Attention Head Count on Transformer Approximation
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks