Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
cs.AI, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Explaining Neural Scaling Laws
- Leveraging redundancy in attention with Reuse Transformers
- Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
- Training Compute-Optimal Large Language Models
- Scaling Laws for Neural Language Models
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
- Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
- Qwen2.5 Technical Report
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