% Key papers for Post-training quantization of LLMs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2023_qlora_67958,
  title = {{QLoRA: Efficient Finetuning of Quantized LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71815},
}

@inproceedings{aaai2020_q_103099,
  title = {{Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6409},
}

@inproceedings{icml2023_smoothquant_43035,
  title = {{SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25228},
}

@inproceedings{aaai2024_owq_6808,
  title = {{OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29237},
}

@inproceedings{neurips2022_zeroquant_65586,
  title = {{ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54407},
}

@inproceedings{aaai2024_agile_5154,
  title = {{Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29860},
}

@inproceedings{neurips2022_outlier_66463,
  title = {{Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54908},
}

@inproceedings{iclr2024_spqr_34389,
  title = {{SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18686},
}

@inproceedings{icml2024_billm_45459,
  title = {{BiLLM: Pushing the Limit of Post-Training Quantization for LLMs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32992},
}

@inproceedings{icml2024_squeezellm_43265,
  title = {{SqueezeLLM: Dense-and-Sparse Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35187},
}

@inproceedings{neurips2021_mqbench_62302,
  title = {{MQBench: Towards Reproducible and Deployable Model Quantization Benchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=TUplOmF8DsM},
}

@inproceedings{aaai2024_exploring_5920,
  title = {{Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29908},
}

@inproceedings{neurips2022_towards_66245,
  title = {{Towards Efficient Post-training Quantization of Pre-trained Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53407},
}

@inproceedings{iclr2024_lut_34928,
  title = {{LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18146},
}

@inproceedings{aaai2025_abq_7950,
  title = {{ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34385},
}

@inproceedings{neurips2024_duquant_73779,
  title = {{DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93727},
}

@inproceedings{iclr2024_zero_34950,
  title = {{ZeRO++: Extremely Efficient Collective Communication for Large Model Training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18124},
}

@inproceedings{iclr2024_omniquant_33752,
  title = {{OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19323},
}

@inproceedings{iclr2024_qllm_34002,
  title = {{QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19073},
}

@inproceedings{aaai2024_norm_6793,
  title = {{Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29815},
}

@inproceedings{neurips2024_onebit_72794,
  title = {{OneBit: Towards Extremely Low-bit Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94602},
}

@inproceedings{cvpr2025_bluelm_25601,
  title = {{BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34136},
}

@inproceedings{neurips2024_shiftaddllm_71550,
  title = {{ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95715},
}

@inproceedings{iclr2025_spinquant_83478,
  title = {{SpinQuant: LLM Quantization with Learned Rotations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28338},
}

@inproceedings{neurips2024_sdp4bit_71989,
  title = {{SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95323},
}

@inproceedings{neurips2024_qtip_70706,
  title = {{QTIP: Quantization with Trellises and Incoherence Processing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96418},
}

@inproceedings{neurips2024_mixture_73943,
  title = {{Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93569},
}