% Key papers for Sparse attention for long-context LLMs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2024_minference_73229,
  title = {{MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94208},
}

@inproceedings{aaai2023_personalized_4361,
  title = {{Personalized Dialogue Generation with Persona-Adaptive Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26518},
}

@inproceedings{neurips2023_focused_69649,
  title = {{Focused Transformer: Contrastive Training for Context Scaling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70287},
}

@inproceedings{neurips2024_videollm_71851,
  title = {{VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95449},
}

@inproceedings{neurips2025_moba_77235,
  title = {{MoBA: Mixture of Block Attention for Long-Context LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=RlqYCpTu1P},
}

@inproceedings{aaai2024_car_5326,
  title = {{CAR-Transformer: Cross-Attention Reinforcement Transformer for Cross-Lingual Summarization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29724},
}

@inproceedings{icml2024_simple_44937,
  title = {{Simple linear attention language models balance the recall-throughput tradeoff}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33515},
}

@inproceedings{neurips2024_streamingdialogue_73155,
  title = {{StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94276},
}

@inproceedings{icml2021_el_39279,
  title = {{EL-Attention: Memory Efficient Lossless Attention for Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9703},
}

@inproceedings{neurips2024_dha_73279,
  title = {{DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94162},
}

@inproceedings{neurips2024_loki_74104,
  title = {{Loki: Low-rank Keys for Efficient Sparse Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93430},
}

@inproceedings{neurips2025_mixture_77139,
  title = {{Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=QuqsEIVWIG},
}

@inproceedings{iclr2025_long_80573,
  title = {{Long Context Compression with Activation Beacon}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31191},
}

@inproceedings{iclr2025_hymba_81113,
  title = {{Hymba: A Hybrid-head Architecture for Small Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30655},
}

@inproceedings{iclr2025_magicpig_81131,
  title = {{MagicPIG: LSH Sampling for Efficient LLM Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30638},
}

@inproceedings{iclr2025_sageattention_81956,
  title = {{SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29829},
}

@inproceedings{icml2024_benchmarking_44000,
  title = {{Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34452},
}

@inproceedings{icml2024_quest_44133,
  title = {{QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34319},
}

@inproceedings{icml2025_hashattention_46642,
  title = {{HashAttention: Semantic Sparsity for Faster Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45928},
}

@inproceedings{icml2025_core_47030,
  title = {{Core Context Aware Transformers for Long Context Language Modeling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45555},
}

@inproceedings{icml2025_m_47156,
  title = {{M+: Extending MemoryLLM with Scalable Long-Term Memory}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45431},
}

@inproceedings{icml2025_star_47254,
  title = {{Star Attention: Efficient LLM Inference over Long Sequences}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45335},
}

@inproceedings{neurips2025_zebra_79049,
  title = {{Zebra-Llama: Towards Extremely Efficient Hybrid Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=l42UGsdrNn},
}