Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control
cs.AI, cs.LG, cs.SY, eess.SY
Submitted: 2026-08-25
Updated: 2026-08-25
Code: https://github.com/fmarrabal/miuracognitive
Terminology
Sources
- Exploring Length Generalization in Large Language Models
- PonderNet: Learning to Ponder
- Universal Transformers
- Feature Transportation Improves Graph Neural Networks
- Looped Transformers for Length Generalization
- Looped Transformers as Programmable Computers
- Adaptive Computation Time for Recurrent Neural Networks
- Neural Turing Machines
- Length Generalization in Arithmetic Transformers
- Transformers Learn Shortcuts to Automata
- Need is All You Need: Homeostatic Neural Networks Adapt to Concept Shift
- The Illusion of State in State-Space Models
- Mixture-of-Depths: Dynamically allocating compute in transformer-based 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