Model-Compression-Paper-List (Quantization)

Model Compression

• LeCun, Yann, John Denker, and Sara Solla. "Optimal brain damage." Advances in neural information processing systems 2 (1989).
• Hinton, Geoffrey. "Distilling the Knowledge in a Neural Network." arXiv preprint arXiv:1503.02531 (2015).
• Han, Song, Huizi Mao, and William J. Dally. "Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding." arXiv preprint arXiv:1510.00149 (2015).
• Han, Song, et al. "EIE: Efficient inference engine on compressed deep neural network." ACM SIGARCH Computer Architecture News 44.3 (2016): 243-254.
• Zoph, B. "Neural architecture search with reinforcement learning." arXiv preprint arXiv:1611.01578 (2016).
• Frankle, Jonathan, and Michael Carbin. "The lottery ticket hypothesis: Finding sparse, trainable neural networks." arXiv preprint arXiv:1803.03635 (2018).
• Hubara, Itay, et al. "Quantized neural networks: Training neural networks with low precision weights and activations." Journal of Machine Learning Research 18.187 (2018): 1-30.
• Liu, Zhuang, et al. "Rethinking the value of network pruning." arXiv preprint arXiv:1810.05270 (2018).
• Heo, Byeongho, et al. "A comprehensive overhaul of feature distillation." Proceedings of the IEEE/CVF international conference on computer vision. 2019.

Quantization

• Courbariaux, Matthieu, Yoshua Bengio, and Jean-Pierre David. "Binaryconnect: Training deep neural networks with binary weights during propagations." Advances in neural information processing systems 28 (2015).
• Choi, Yoojin, Mostafa El-Khamy, and Jungwon Lee. "Towards the limit of network quantization." arXiv preprint arXiv:1612.01543 (2016).
• Lin, Darryl, Sachin Talathi, and Sreekanth Annapureddy. "Fixed point quantization of deep convolutional networks." International conference on machine learning. PMLR, 2016.
• Zhou, Shuchang, et al. "Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients." arXiv preprint arXiv:1606.06160 (2016).
• Cheng, Yu, et al. "Model compression and acceleration for deep neural networks: The principles, progress, and challenges." IEEE Signal Processing Magazine 35.1 (2018): 126-136
• Krishnamoorthi, Raghuraman. "Quantizing deep convolutional networks for efficient inference: A whitepaper." arXiv preprint arXiv:1806.08342 (2018).
• Hubara, Itay, et al. "Quantized neural networks: Training neural networks with low precision weights and activations." Journal of Machine Learning Research 18.187 (2018): 1-30.
• Fan, Angela, et al. "Training with quantization noise for extreme model compression." arXiv preprint arXiv:2004.07320 (2020).
• Deng, Lei, et al. "Model compression and hardware acceleration for neural networks: A comprehensive survey." Proceedings of the IEEE 108.4 (2020): 485-532.
• Li, Yuhang, et al. "Brecq: Pushing the limit of post-training quantization by block reconstruction." arXiv preprint arXiv:2102.05426 (2021)
• Gholami, Amir, et al. "A survey of quantization methods for efficient neural network inference." Low-Power Computer Vision. Chapman and Hall/CRC, 2022. 291-326.
• Lee, Junghyup, et al. "Scheduling Weight Transitions for Quantization-Aware Training." arXiv preprint arXiv:2404.19248 (2024). (ICCV 2025)

Zero-Shot Quantization (Data-Free Quantization)

• Nagel, Markus, et al. "Data-free quantization through weight equalization and bias correction." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.
• Choi, Yoojin, et al. "Data-free network quantization with adversarial knowledge distillation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020.
• Cai, Yaohui, et al. "Zeroq: A novel zero shot quantization framework." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020.
• Xu, Shoukai, et al. "Generative low-bitwidth data free quantization." Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XII 16. Springer International Publishing, 2020.

Data Generation (Zero-Shot Quantization)

• Xu, Shoukai, et al. "Generative low-bitwidth data free quantization." Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XII 16. Springer International Publishing, 2020.
• Zhang, Xiangguo, et al. "Diversifying sample generation for accurate data-free quantization." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021.
• Choi, Kanghyun, et al. "Qimera: Data-free quantization with synthetic boundary supporting samples." Advances in Neural Information Processing Systems 34 (2021): 14835-14847.
• Zhong, Yunshan, et al. "Intraq: Learning synthetic images with intra-class heterogeneity for zero-shot network quantization." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
• Li, Huantong, et al. "Hard sample matters a lot in zero-shot quantization." Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition. 2023.
• Qian, Biao, et al. "Rethinking data-free quantization as a zero-sum game." Proceedings of the AAAI conference on artificial intelligence. Vol. 37. No. 8. 2023.
• Qian, Biao, et al. "Adaptive data-free quantization." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.
• Chen, Xinrui, et al. "TexQ: zero-shot network quantization with texture feature distribution calibration." Advances in Neural Information Processing Systems 36 (2024).
• Bai, Jianhong, et al. "Robustness-Guided Image Synthesis for Data-Free Quantization." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 10. 2024.
• Li, Yuhang, et al. "GenQ: Quantization in Low Data Regimes with Generative Synthetic Data." European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024.
• Ramachandran, Akshat, et al. "OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models." arXiv preprint arXiv:2503.10959 (2025). (ICCV 2025)
• Li, Changhao, et al. "Task-Specific Zero-shot Quantization-Aware Training for Object Detection." arXiv preprint arXiv:2507.16782 (2025). (ICCV 2025)

Model Training (Zero-Shot Quantization)

• Guo, Cong, et al. "Squant: On-the-fly data-free quantization via diagonal hessian approximation." arXiv preprint arXiv:2202.07471 (2022).
• Choi, Kanghyun, et al. "It's all in the teacher: Zero-shot quantization brought closer to the teacher." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
• Shang, Yuzhang, et al. "Enhancing Post-training Quantization Calibration through Contrastive Learning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
• Li, Yuhang, et al. "GenQ: Quantization in Low Data Regimes with Generative Synthetic Data." European Conference on Computer Vision. Springer, Cham, 2025.
• Hong, Inpyo, et al. "Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing." arXiv preprint arXiv:2412.19125 (2024).
• Kim, Minjun, et al. "SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning", The Thirteenth International Conference on Learning Representations (ICLR), 2025.
• Zhong, Yunshan, et al. "Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers" arXiv preprint arXiv:2412.16553 (2024). (ICCV 2025)

LLM Quantization

• Dettmers, Tim, et al. "Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale." Advances in Neural Information Processing Systems 35 (2022): 30318-30332.
• Yao, Zhewei, et al. "Zeroquant: Efficient and affordable post-training quantization for large-scale transformers." Advances in Neural Information Processing Systems 35 (2022): 27168-27183.
• Wu, Xiaoxia, et al. "Understanding int4 quantization for language models: latency speedup, composability, and failure cases." International Conference on Machine Learning. PMLR, 2023.
• Liu, Zirui, et al. "Kivi: A tuning-free asymmetric 2bit quantization for kv cache." arXiv preprint arXiv:2402.02750 (2024).
• Zhang, Cheng, et al. "LQER: Low-Rank Quantization Error Reconstruction for LLMs." arXiv preprint arXiv:2402.02446 (2024).
• Huang, Wei, et al. "Billm: Pushing the limit of post-training quantization for llms." arXiv preprint arXiv:2402.04291 (2024).
• Guo, Jinyang, et al. "Compressing large language models by joint sparsification and quantization." Forty-first International Conference on Machine Learning. 2024.
• Yao, Zhewei, et al. "Exploring post-training quantization in llms from comprehensive study to low rank compensation." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 17. 2024.
• Li, Liang, et al. "Norm tweaking: High-performance low-bit quantization of large language models." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 17. 2024.
• Heo, Jung Hwan, et al. "Rethinking channel dimensions to isolate outliers for low-bit weight quantization of large language models." arXiv preprint arXiv:2309.15531 (2023).
• Liu, Jing, et al. "Qllm: Accurate and efficient low-bitwidth quantization for large language models." arXiv preprint arXiv:2310.08041 (2023).
• Zhao, Weibo, et al. "ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization." arXiv preprint arXiv:2411.07762 (2024).(AAAI 2025)

Generative Model Quantization

Stable Diffusion (UNet)

• Shang, Yuzhang, et al. "Post-training quantization on diffusion models." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023.
• Li, Xiuyu, et al. "Q-diffusion: Quantizing diffusion models." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.
• Sui, Yang, et al. "Bitsfusion: 1.99 bits weight quantization of diffusion model." arXiv preprint arXiv:2406.04333 (2024). (NeurIPS 2024)
• Tang, Siao, et al. "Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing." arXiv preprint arXiv:2311.06322 (2023). (ECCV 2024)
• Li, Muyang, et al. "Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models." arXiv preprint arXiv:2411.05007 (2024). (ICLR 2025)
• Ryu, Hyogon, NaHyeon Park, and Hyunjung Shim. "Dgq: Distribution-aware group quantization for text-to-image diffusion models." arXiv preprint arXiv:2501.04304 (2025). (ICLR 2025)
• Lee, Dongyeun, et al. "DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization." arXiv preprint arXiv:2507.12933 (2025). (ICCV 2025)
• Wang, Haoxuan, et al. "Quest: Low-bit diffusion model quantization via efficient selective finetuning." arXiv preprint arXiv:2402.03666 (2024). (ICCV 2025)
• Memory-Efficient Generative Models via Product Quantization (ICCV 2025, TBD)

DiT (Diffusion Transformer)

• Wu, Junyi, et al. "Ptq4dit: Post-training quantization for diffusion transformers." arXiv preprint arXiv:2405.16005 (2024). (NeurIPS 2024)
• Deng, Juncan, et al. "Vq4dit: Efficient post-training vector quantization for diffusion transformers." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. No. 15. 2025.
• Dong, Zhenyuan, and Sai Qian Zhang. "DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing." arXiv preprint arXiv:2409.07756 (2024). (WACV 2025 Accepted)
• Chen, Lei, et al. "Q-dit: Accurate post-training quantization for diffusion transformers." arXiv preprint arXiv:2406.17343 (2024). (CVPR 2025 Accepted)
• Zhao, Tianchen, et al. "Vidit-q: Efficient and accurate quantization of diffusion transformers for image and video generation." arXiv preprint arXiv:2406.02540 (2024). (ICLR 2025 Accepted)

Vector Quantization

• Kim, Youngeun, et al. "Task vector quantization for memory-efficient model merging." arXiv preprint arXiv:2503.06921 (2025). (ICCV 2025)
• Li, Shuaiting, et al. "SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting." arXiv preprint arXiv:2503.08668 (2025). (ICCV 2025)
• Deng, Juncan, et al. "ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba." arXiv preprint arXiv:2503.09509 (2025). (ICCV 2025)