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

@inproceedings{neurips2022_confident_66265,
  title = {{Confident Adaptive Language Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53256},
}

@inproceedings{aaai2024_hot_6219,
  title = {{Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27798},
}

@inproceedings{icml2024_medusa_44319,
  title = {{Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34133},
}

@inproceedings{iclr2024_skeleton_35193,
  title = {{Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17880},
}

@inproceedings{aaai2021_adaptive_83,
  title = {{Adaptive Beam Search Decoding for Discrete Keyphrase Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13082-adaptive-beam-search-decoding-for-discrete-keyphrase-generation/},
}

@inproceedings{neurips2024_grammar_70509,
  title = {{Grammar-Aligned Decoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96599},
}

@inproceedings{neurips2024_padellm_74374,
  title = {{PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93190},
}

@inproceedings{icml2024_distillm_45255,
  title = {{DistiLLM: Towards Streamlined Distillation for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33197},
}

@inproceedings{icml2024_guiding_45414,
  title = {{Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33037},
}

@inproceedings{neurips2024_accelerating_71064,
  title = {{Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96146},
}

@inproceedings{aaai2025_adaptive_8027,
  title = {{Adaptive Draft-Verification for Efficient Large Language Model Decoding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34647},
}

@inproceedings{icml2023_arithmetic_41872,
  title = {{Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24273},
}

@inproceedings{icml2025_flexible_46967,
  title = {{Flexible and Efficient Grammar-Constrained Decoding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45613},
}

@inproceedings{neurips2024_superposed_71608,
  title = {{Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95663},
}

@inproceedings{neurips2024_nearest_71885,
  title = {{Nearest Neighbor Speculative Decoding for LLM Generation and Attribution}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95418},
}

@inproceedings{neurips2025_multiverse_79607,
  title = {{Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=r9YDEErKXU},
}

@inproceedings{neurips2025_accelerating_80271,
  title = {{Accelerating Diffusion LLMs via Adaptive Parallel Decoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=xwqTt26NJf},
}

@inproceedings{iclr2025_controlled_81336,
  title = {{Controlled LLM Decoding via Discrete Auto-regressive Biasing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30436},
}

@inproceedings{aaai2025_multi_10007,
  title = {{Multi-Branch Self-Drafting for LLM Inference Acceleration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34567},
}

@inproceedings{iclr2024_mbr_34749,
  title = {{MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18325},
}

@inproceedings{icml2024_when_43581,
  title = {{When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34871},
}

@inproceedings{icml2024_cllms_43625,
  title = {{CLLMs: Consistency Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34827},
}

@inproceedings{icml2024_promises_43731,
  title = {{Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34721},
}