# Numerical Pruning for Efficient Autoregressive Models

arXiv: https://arxiv.org/abs/2412.12441 · HTML: https://mlsanity.com/paper/2412.12441/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 56 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge](https://mlsanity.com/paper/2312.05693/) (2023)
- [Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization](https://mlsanity.com/paper/2206.01198/) (2022)
- [Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training](https://mlsanity.com/paper/2211.10801/) (2022)

## Built on by (most cited first, 25 of 25)

- [VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting](https://mlsanity.com/paper/2507.05116/) (2025)
- [High-Order Matching for One-Step Shortcut Diffusion Models](https://mlsanity.com/paper/2502.00688/) (2025)
- [Structured Agent Distillation for Large Language Model](https://mlsanity.com/paper/2505.13820/) (2025)
- [Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling](https://mlsanity.com/paper/2502.08150/) (2025)
- [Integrating Large Language Models for Automated Structural Analysis](https://mlsanity.com/paper/2504.09754/) (2025)
- [FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge](https://mlsanity.com/paper/2505.14709/) (2025)
- [QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge](https://mlsanity.com/paper/2503.16709/) (2025)
- [Automating Structural Engineering Workflows with Large Language Model Agents](https://mlsanity.com/paper/2510.11004/) (2025)
- [Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA](https://mlsanity.com/paper/2512.22208/) (2025)
- [Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers](https://mlsanity.com/paper/2501.10688/) (2025)
- [A Survey on Foundation Models for Personalized Federated Intelligence](https://mlsanity.com/paper/2505.06907/) (2025)
- [Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding](https://mlsanity.com/paper/2503.11108/) (2025)
- [Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs](https://mlsanity.com/paper/2506.00577/) (2025)
- [Training-free Token Reduction for Vision Mamba](https://mlsanity.com/paper/2507.14042/) (2025)
- [RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing](https://mlsanity.com/paper/2509.12168/) (2025)
- [ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation](https://mlsanity.com/paper/2511.12893/) (2025)
- [ModHiFi: Identifying High Fidelity predictive components for Model Modification](https://mlsanity.com/paper/2511.19566/) (2025)
- [GRAIL: Post-hoc Compensation by Linear Reconstruction for Compressed Networks](https://mlsanity.com/paper/2602.23795/) (2026)
- [ActTail: Global Activation Sparsity in Large Language Models](https://mlsanity.com/paper/2603.12272/) (2026)
- [NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices](https://mlsanity.com/paper/2504.03118/) (2025)
- [SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation](https://mlsanity.com/paper/2507.03415/) (2025)
- [IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning](https://mlsanity.com/paper/2507.14171/) (2025)
- [Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT](https://mlsanity.com/paper/2608.13681/) (2026)
- [LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception](https://mlsanity.com/paper/2609.39938/) (2026)
- [From Patching to Pruning Visual Computation in Vision Language Models](https://mlsanity.com/paper/2610.03389/) (2026)

## Abstract (arXiv)

Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.