The Cost of Long Memory: State, Context, and Stability Complexity in Sequence Models
cs.LG
Submitted: 2026-09-24
Updated: 2026-09-24
Sources
- L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- VORT: Adaptive Power-Law Memory for NLP Transformers
- Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
- LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement
- Tuning Frequency Bias of State Space 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