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

@inproceedings{neurips2024_kvquant_70145,
  title = {{KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96936},
}

@inproceedings{neurips2024_quarot_73101,
  title = {{QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94328},
}

@inproceedings{neurips2024_minicache_74162,
  title = {{MiniCache: KV Cache Compression in Depth Dimension for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93380},
}

@inproceedings{neurips2024_zipcache_70550,
  title = {{ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96563},
}

@inproceedings{neurips2024_kv_73954,
  title = {{KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93558},
}

@inproceedings{aaai2026_flashsvd_107368,
  title = {{FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39720},
}

@inproceedings{aaai2025_qjl_10408,
  title = {{QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34773},
}

@inproceedings{icml2024_extreme_43488,
  title = {{Extreme Compression of Large Language Models via Additive Quantization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34964},
}

@inproceedings{neurips2024_pv_72722,
  title = {{PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94666},
}

@inproceedings{neurips2024_compressing_73689,
  title = {{Compressing Large Language Models using Low Rank and Low Precision Decomposition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93805},
}

@inproceedings{cvpr2025_casp_25640,
  title = {{CASP: Compression of Large Multimodal Models Based on Attention Sparsity}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32507},
}

@inproceedings{icml2025_lexico_47699,
  title = {{Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44898},
}

@inproceedings{neurips2025_70_80239,
  title = {{70\% Size, 100\% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=xdNAVP7TGy},
}

@inproceedings{iclr2025_stbllm_80889,
  title = {{STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30878},
}

@inproceedings{iclr2025_svd_81777,
  title = {{SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30003},
}

@inproceedings{iclr2025_basis_83004,
  title = {{Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28800},
}

@inproceedings{iclr2026_kv_87332,
  title = {{KV-Cache Transform Coding for Compact Storage in LLM Inference}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=aNVKROYpLB},
}

@inproceedings{aaai2026_kvmix_108070,
  title = {{KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40422},
}

@inproceedings{icml2024_excp_45071,
  title = {{ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33381},
}

@inproceedings{icml2025_slim_46079,
  title = {{SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46479},
}