Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence
cs.LG
Submitted: 2026-09-30
Updated: 2026-10-06
Code: https://github.com/Botwwt/sparc
Sources
- RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Efficiently Modeling Long Sequences with Structured State Spaces
- GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling
- Adam: A Method for Stochastic Optimization
- Decoupled Weight Decay Regularization
- A Practical Sparse Approximation for Real Time Recurrent Learning
- POPGym: Benchmarking Partially Observable Reinforcement Learning
- Proximal Policy Optimization Algorithms
- Simplified State Space Layers for Sequence Modeling
- Unbiased Online Recurrent Optimization
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