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

@inproceedings{neurips2017_soft_56673,
  title = {{Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8907},
}

@inproceedings{neurips2019_post_58816,
  title = {{Post training 4-bit quantization of convolutional networks for rapid-deployment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13871},
}

@inproceedings{iclr2018_model_28584,
  title = {{Model compression via distillation and quantization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/8},
}

@inproceedings{cvpr2022_nonuniform_19469,
  title = {{Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2021_training_30482,
  title = {{Training with Quantization Noise for Extreme Model Compression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2772},
}

@inproceedings{icml2020_accelerating_37896,
  title = {{Accelerating Large-Scale Inference with Anisotropic Vector Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6689},
}

@inproceedings{cvpr2018_quantization_13495,
  title = {{Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Xu_Quantization_of_Fully_CVPR_2018_paper.html},
}

@inproceedings{iclr2018_loss_28455,
  title = {{Loss-aware Weight Quantization of Deep Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/203},
}

@inproceedings{cvpr2021_diversifying_16893,
  title = {{Diversifying Sample Generation for Accurate Data-Free Quantization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_zero_18162,
  title = {{Zero-Shot Adversarial Quantization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{iclr2020_and_29782,
  title = {{And the Bit Goes Down: Revisiting the Quantization of Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rJehVyrKwH},
}

@inproceedings{iclr2017_towards_28358,
  title = {{Towards the Limit of Network Quantization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=rJ8uNptgl},
}

@inproceedings{iclr2019_spreading_29058,
  title = {{Spreading vectors for similarity search}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1005},
}

@inproceedings{icml2020_up_38913,
  title = {{Up or Down? Adaptive Rounding for Post-Training Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6482},
}

@inproceedings{iclr2018_variational_28708,
  title = {{Variational Network Quantization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/131},
}

@inproceedings{cvpr2020_structured_16296,
  title = {{Structured Compression by Weight Encryption for Unstructured Pruning and Quantization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{iclr2021_brecq_30276,
  title = {{BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2596},
}

@inproceedings{neurips2018_gradiveq_57181,
  title = {{GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11501},
}

@inproceedings{neurips2022_optimal_65825,
  title = {{Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53412},
}

@inproceedings{cvpr2021_distribution_16886,
  title = {{Distribution-Aware Adaptive Multi-Bit Quantization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2025_automatic_25541,
  title = {{Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34889},
}

@inproceedings{cvpr2025_quantization_27339,
  title = {{Quantization without Tears}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34679},
}

@inproceedings{aaai2025_adaptive_8025,
  title = {{Adaptive Dataset Quantization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33317},
}

@inproceedings{cvpr2025_enhancing_26138,
  title = {{Enhancing Diversity for Data-free Quantization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33597},
}

@inproceedings{neurips2024_magr_72365,
  title = {{MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94986},
}

@inproceedings{neurips2024_qbb_71643,
  title = {{QBB: Quantization with Binary Bases for LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95634},
}

@inproceedings{neurips2024_learning_73086,
  title = {{Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94342},
}

@inproceedings{iclr2025_effective_83969,
  title = {{Effective Interplay between Sparsity and Quantization: From Theory to Practice}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27855},
}

@inproceedings{iclr2026_robust_87667,
  title = {{Robust Training of Neural Networks at Arbitrary Precision and Sparsity}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=e6nZrzSccj},
}

@inproceedings{aaai2026_dynaquant_106157,
  title = {{DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38464},
}

@inproceedings{iclr2024_network_33487,
  title = {{Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19588},
}

@inproceedings{icml2025_layer_46867,
  title = {{Layer-wise Quantization for Quantized Optimistic Dual Averaging}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45711},
}

@inproceedings{icml2025_qt_47143,
  title = {{QT-DoG: Quantization-Aware Training for Domain Generalization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45444},
}

@inproceedings{icml2026_float8_49293,
  title = {{Float8@2bits: Entropy Coding Enables Data-Free Model Compression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=15SdFmonYz},
}

@inproceedings{icml2026_sign_53087,
  title = {{Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=bxVWc9Mzns},
}

@inproceedings{icml2026_watersic_53401,
  title = {{WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=fCPgAHIciE},
}

@inproceedings{neurips2025_binary_75195,
  title = {{Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=5MGClYw1cR},
}

@inproceedings{neurips2025_switchable_75444,
  title = {{Switchable Token-Specific Codebook Quantization For Face Image Compression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=8AtYSW3VdX},
}

@inproceedings{iclr2025_on_80729,
  title = {{On Quantizing Neural Representation for Variable-Rate Video Coding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31039},
}

@inproceedings{iclr2025_approaching_82288,
  title = {{Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29503},
}