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

@inproceedings{neurips2023_speculative_67427,
  title = {{Speculative Decoding with Big Little Decoder}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72306},
}

@inproceedings{icml2024_eagle_43299,
  title = {{EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35153},
}

@inproceedings{neurips2025_eagle_75136,
  title = {{EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=4exx1hUffq},
}

@inproceedings{neurips2024_specexec_71531,
  title = {{SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95733},
}

@inproceedings{iclr2024_distillspec_35393,
  title = {{DistillSpec: Improving Speculative Decoding via Knowledge Distillation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17680},
}

@inproceedings{neurips2024_cascade_73672,
  title = {{Cascade Speculative Drafting for Even Faster LLM Inference}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93820},
}

@inproceedings{neurips2024_sequoia_74118,
  title = {{Sequoia: Scalable and Robust Speculative Decoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93418},
}

@inproceedings{aaai2025_dynamic_8855,
  title = {{Dynamic-Width Speculative Beam Decoding for LLM Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34690},
}

@inproceedings{icml2024_online_43728,
  title = {{Online Speculative Decoding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34724},
}

@inproceedings{icml2024_break_44940,
  title = {{Break the Sequential Dependency of LLM Inference Using Lookahead Decoding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33512},
}

@inproceedings{neurips2025_specreason_80106,
  title = {{SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wCbOKbZ7kf},
}

@inproceedings{neurips2024_kangaroo_73663,
  title = {{Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93829},
}

@inproceedings{aaai2025_falcon_9141,
  title = {{Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34566},
}

@inproceedings{icml2025_reward_46398,
  title = {{Reward-Guided Speculative Decoding for Efficient LLM Reasoning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46166},
}

@inproceedings{neurips2024_speculative_73945,
  title = {{Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93567},
}

@inproceedings{neurips2024_a_74417,
  title = {{A Theoretical Perspective for Speculative Decoding Algorithm}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93154},
}

@inproceedings{neurips2025_griffin_76491,
  title = {{GRIFFIN: Effective Token Alignment for Faster Speculative Decoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=JwnAItQF9v},
}

@inproceedings{neurips2025_scaling_76495,
  title = {{Scaling Speculative Decoding with Lookahead Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=JxxKj8pow1},
}

@inproceedings{neurips2025_autojudge_79028,
  title = {{AutoJudge: Judge Decoding Without Manual Annotation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ktNJgpmjjP},
}

@inproceedings{neurips2025_suffixdecoding_79988,
  title = {{SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=uwL0vbeEVn},
}

@inproceedings{iclr2025_efficient_81124,
  title = {{Efficient Inference for Large Language Model-based Generative Recommendation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30645},
}