Non-Commutative State Tracking with Input-Dependent Low-Rank Updates in Mamba-3

arXiv:2609.28273 · eess.SY, cs.LG, cs.SY · Submitted 2026-09-23 · Read on arXiv

eess.SY, cs.LG, cs.SY

Submitted: 2026-09-23

Updated: 2026-09-26

Code: https://github.com/state-spaces/mamba

Terminology

• Accuracy — 19× in this paper · explained in 1 episode
• Embeddings — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Transformer — 5× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Covariate Shift — 1× in this paper · explained in 2 episodes

Sources

• DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
• RWKV-7 "Goose" with Expressive Dynamic State Evolution
• Dissecting Linear Recurrent Models: How Different Gating Strategies Drive Selectivity and Generalization
• MTIL: Encoding Full History with Mamba for Temporal Imitation Learning

Related papers

• One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing
• A Geometric Decision Procedure for STL Feasibility and Repair
• Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
• Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
• Minimal Experiments for Robust Stabilization: Information, Spectral Geometry, and Duration
• Decentralized Power-Optimal Coordination for Spacecraft Swarms Using Time-Varying Magnetorquer Actuation