Model Compression & Pruning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Essential papers on compressing neural networks — from pruning and lottery tickets to structured sparsity and efficient deployment.

Model Compression & Pruning: 10 key papers

1. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
   Han et al. arXiv 2015.
2. Learning both Weights and Connections for Efficient Neural Networks
   Han et al. arXiv 2015.
3. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
   Frankle and Carbin. arXiv 2018.
4. What is the State of Neural Network Pruning?
   Blalock et al. arXiv 2020.
5. Rethinking the Value of Network Pruning
   Liu et al. arXiv 2018.
6. Pruning Filters for Efficient ConvNets
   Li et al. arXiv 2016.
7. SNIP: Single-shot Network Pruning based on Connection Sensitivity
   Lee et al. arXiv 2018.
8. Movement Pruning: Adaptive Sparsity by Fine-Tuning
   Sanh et al. arXiv 2020.
9. A Survey of Model Compression and Acceleration for Deep Neural Networks
   Cheng et al. arXiv 2017.
10. SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
    Frantar and Alistarh. arXiv 2023.

Related reading lists

• Quantization for Efficient Inference
• Scaling Laws and Emergent Capabilities
• In-Context RL & Prompting
• State Space Models & Structured SSMs
• Efficient Transformers
• Adaptive Sensing and Active Learning
• Zero-Shot RL & Generalization
• Offline-to-Online RL & Fine-Tuning