% Key papers for Ultra-low-bit LLM quantization (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2020_bayesian_59437,
  title = {{Bayesian Bits: Unifying Quantization and Pruning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18855},
}

@inproceedings{neurips2022_q_65606,
  title = {{Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55349},
}

@inproceedings{cvpr2021_square_17939,
  title = {{Square Root Bundle Adjustment for Large-Scale Reconstruction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_layer_17247,
  title = {{Layer-Wise Searching for 1-Bit Detectors}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{icml2023_the_42751,
  title = {{The case for 4-bit precision: k-bit Inference Scaling Laws}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23915},
}

@inproceedings{aaai2023_adaptive_3074,
  title = {{Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25564},
}

@inproceedings{cvpr2023_nipq_21642,
  title = {{NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21329},
}

@inproceedings{cvpr2024_jointsq_23855,
  title = {{JointSQ: Joint Sparsification-Quantization for Distributed Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31122},
}

@inproceedings{cvpr2023_cabm_20520,
  title = {{CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22741},
}

@inproceedings{aaai2024_ptmq_6908,
  title = {{PTMQ: Post-training Multi-Bit Quantization of Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29553},
}

@inproceedings{aaai2024_aq_5102,
  title = {{AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29487},
}

@inproceedings{neurips2023_packqvit_67887,
  title = {{PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71880},
}

@inproceedings{aaai2025_mpq_9868,
  title = {{MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33823},
}

@inproceedings{aaai2025_pushing_10402,
  title = {{Pushing the Limits of BFP on Narrow Precision LLM Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35407},
}

@inproceedings{neurips2023_quantsr_66742,
  title = {{QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72890},
}

@inproceedings{neurips2025_sageattention3_76464,
  title = {{SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=JbJVWljk7r},
}

@inproceedings{aaai2025_thinking_10994,
  title = {{Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32843},
}

@inproceedings{icml2025_quest_46822,
  title = {{QuEST: Stable Training of LLMs with 1-Bit Weights and Activations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45754},
}

@inproceedings{icml2025_slim_47199,
  title = {{SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45388},
}

@inproceedings{icml2025_mxmoe_48626,
  title = {{MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43995},
}

@inproceedings{icml2025_optimizing_48890,
  title = {{Optimizing Large Language Model Training Using FP4 Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43733},
}

@inproceedings{neurips2025_fp4_79033,
  title = {{FP4 All the Way: Fully Quantized Training of Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=kuzye4EPLR},
}

@inproceedings{aaai2026_mix_100527,
  title = {{Mix-QSAM2: Mixed-Precision Quantization for High Fidelity Segmentation in Resource Constrained Scenarios}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37374},
}

@inproceedings{icml2024_sfc_44995,
  title = {{SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33457},
}

@inproceedings{icml2025_blockdialect_47661,
  title = {{BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44936},
}

@inproceedings{icml2025_sageattention2_48505,
  title = {{SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44114},
}

@inproceedings{icml2025_bimacosr_49097,
  title = {{BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43527},
}

@inproceedings{icml2026_tetrajet_49956,
  title = {{TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=7ZQhm5HnOA},
}

@inproceedings{icml2026_quartet_50470,
  title = {{Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=CciWEZZDVb},
}

@inproceedings{icml2026_autoqra_50618,
  title = {{AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=EB8MHApOav},
}