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

@inproceedings{neurips2023_h2o_68142,
  title = {{H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71645},
}

@inproceedings{icml2023_deja_43152,
  title = {{Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23704},
}

@inproceedings{neurips2024_efficient_74445,
  title = {{Efficient LLM Scheduling by Learning to Rank}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93127},
}

@inproceedings{neurips2023_response_68909,
  title = {{Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70953},
}

@inproceedings{aaai2025_portcullis_10327,
  title = {{Portcullis: A Scalable and Verifiable Privacy Gateway for Third-Party LLM Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32088},
}

@inproceedings{icml2024_better_45403,
  title = {{Better \& Faster Large Language Models via Multi-token Prediction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33048},
}

@inproceedings{neurips2025_what_80425,
  title = {{What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=zPKeJAEo27},
}

@inproceedings{aaai2026_tokenpowerbench_108183,
  title = {{TokenPowerBench: Benchmarking the Power Consumption of LLM Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40535},
}

@inproceedings{iclr2024_relu_35268,
  title = {{ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17805},
}

@inproceedings{neurips2024_d_72375,
  title = {{D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94977},
}

@inproceedings{neurips2024_effilearner_71627,
  title = {{EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95648},
}

@inproceedings{icml2024_any_45606,
  title = {{Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32846},
}

@inproceedings{icml2024_ee_45731,
  title = {{EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32721},
}

@inproceedings{neurips2025_understanding_77053,
  title = {{Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Q3qAsZAEZw},
}

@inproceedings{neurips2025_vision_77885,
  title = {{Vision-centric Token Compression in Large Language Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=YdggdEL41C},
}

@inproceedings{neurips2024_rethinking_70442,
  title = {{Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96664},
}

@inproceedings{neurips2024_nomad_70485,
  title = {{NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96623},
}

@inproceedings{neurips2025_hygen_78227,
  title = {{HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=cQxLCVa9u7},
}

@inproceedings{iclr2025_semantics_81006,
  title = {{Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30762},
}

@inproceedings{aaai2025_adaskip_8020,
  title = {{AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34579},
}

@inproceedings{icml2024_chai_45751,
  title = {{CHAI: Clustered Head Attention for Efficient LLM Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32701},
}

@inproceedings{icml2025_puzzle_47314,
  title = {{Puzzle: Distillation-Based NAS for Inference-Optimized LLMs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45275},
}

@inproceedings{neurips2024_sirius_70532,
  title = {{SIRIUS : Contexual Sparisty with Correction for Efficient LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96580},
}