The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
cs.LG, cs.AI
Submitted: 2026-08-24
Updated: 2026-09-28
Terminology
Sources
- Generating Long Sequences with Sparse Transformers
- RWKV: Reinventing RNNs for the Transformer Era
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
- WaveNet: A Generative Model for Raw Audio
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Deep Neural Network Ensembles for Time Series Classification
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