Constant-Memory Recall: Learned Associations in a Fixed Matrix State
cs.LG
Submitted: 2026-09-23
Updated: 2026-09-23
Sources
- Zoology: Measuring and Improving Recall in Efficient Language Models
- Using Fast Weights to Attend to the Recent Past
- Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
- Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
- Revisiting associative recall in modern recurrent models
- Linear Transformers Are Secretly Fast Weight Programmers
- Attention Is All You Need
- Efficient Streaming Language Models with Attention Sinks
- Gated Delta Networks: Improving Mamba2 with Delta Rule
- Parallelizing Linear Transformers with the Delta Rule over Sequence Length
- H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language 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