ADPTNet: Adaptive with Prescriptive Timescales Non-Linear SSM for Sequence Modelling
cs.NE, cs.AI, cs.DC, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/proger/accelerated-scan
Terminology
Sources
- Q-S5: Towards Quantized State Space Models
- Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models
- Trellis Networks for Sequence Modeling
- It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
- Deep Rewiring: Training very sparse deep networks
- STDP as presynaptic activity times rate of change of postsynaptic activity
- RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Lipschitz Recurrent Neural Networks
- SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
- Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
- Hungry Hungry Hippos: Towards Language Modeling with State Space Models
- The State of Sparsity in Deep Neural Networks
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Efficiently Modeling Long Sequences with Structured State Spaces
- How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections
- HyperNetworks
- Instability of the Sherman-Morrison formula and stabilization by iterative refinement
Related papers
- Evolutionary Ensemble of Agents
- Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
- Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
- Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations
- Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
- S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning