An Input-Dependent Readout Phase for Resonant Sequence Models

cs.LG, cs.CL

Submitted: 2026-09-26

Updated: 2026-09-26

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Zoology: Measuring and Improving Recall in Efficient Language Models
• Simple linear attention language models balance the recall-throughput tradeoff
• ResonatorLM: Causal Resonant Field Mixing for Efficient Long-Context Language Modeling
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
• Kimi Linear: An Expressive, Efficient Attention Architecture
• Mamba-3: Improved Sequence Modeling using State Space Principles
• RoFormer: Enhanced Transformer with Rotary Position Embedding

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