Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
cs.LG, cs.AI, cs.PF
Submitted: 2026-05-15
Updated: 2026-11-07
Code: https://github.com/daniel-eai/ghosted_layers_official_repository
Terminology
Sources
- Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
- The Llama 3 Herd of Models
- Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods
- GPT-4 Technical Report
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- LLaMA: Open and Efficient Foundation Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
- Qwen3 Technical Report
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis