# CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers

arXiv: https://arxiv.org/abs/2602.05243 · HTML: https://mlsanity.com/paper/2602.05243/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [An Introduction to Matrix Concentration Inequalities](https://mlsanity.com/paper/1501.01571/) (2015)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers](https://mlsanity.com/paper/2305.17328/) (2023)
- [Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs](https://mlsanity.com/paper/2310.08915/) (2023)
- [Gradient-Free Structured Pruning with Unlabeled Data](https://mlsanity.com/paper/2303.04185/) (2023)
- [The Need for Speed: Pruning Transformers with One Recipe](https://mlsanity.com/paper/2403.17921/) (2024)
- [Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework](https://mlsanity.com/paper/2411.18376/) (2024)
- [Dense Vision Transformer Compression with Few Samples](https://mlsanity.com/paper/2403.18708/) (2024)
- [Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression](https://mlsanity.com/paper/2403.15835/) (2024)
- [Olica: Efficient Structured Pruning of Large Language Models without Retraining](https://mlsanity.com/paper/2506.08436/) (2025)
- [Variance-Based Pruning for Accelerating and Compressing Trained Networks](https://mlsanity.com/paper/2507.12988/) (2025)
- [Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer](https://mlsanity.com/paper/2408.17062/) (2024)

## Built on by (most cited first, 2 of 2)

- [QK-Wanda: Coupling Queries and Keys for Unstructured Pruning](https://mlsanity.com/paper/2610.01554/) (2026)
- [Retraining-Free Depth Pruning of Vision Transformers: A Cross Domain Study of Layer Redundancy](https://mlsanity.com/paper/2610.15005/) (2026)

## Abstract (arXiv)

Transformers achieve strong accuracy but incur high compute and memory cost. Structured pruning reduces inference cost, but most methods rely on retraining or multi-stage optimization, which limits post-training deployment. We propose CORP, a closed-form one-shot structured pruning method that removes MLP dimensions and attention substructures using only unlabeled calibration data without gradients or fine-tuning. CORP formulates structured pruning as a representation recovery problem. It models removed components as affine functions of retained components and derives closed-form ridge regression solutions that fold compensation into model weights. This minimizes a layer-local affine/logit reconstruction objective under the calibration distribution. Experiments on ImageNet with DeiT reveal strong redundancy in both MLP and attention representations. With CORP, models retain high accuracy under aggressive sparsity. On DeiT-Huge, CORP achieves 83.27% Top-1 accuracy after pruning 50% of both MLP and attention structures.