Residual Streams Read, Recurrent States Remember: The Global Workspace in Mamba Models
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Mamba-3: Improved Sequence Modeling using State Space Principles
- Does Transformer Interpretability Transfer to RNNs?
- Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?
- Scaling Latent Reasoning via Looped Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection