Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Feature Purification: How Adversarial Training Performs Robust Deep Learning
- Adversarial Robustness as a Prior for Learned Representations
- Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
- Adversarial Examples Are Not Bugs, They Are Superposition
- Bridging Adversarial Robustness and Gradient Interpretability
- Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights
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
- Agents' Last Exam
- 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