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

@inproceedings{neurips2019_xlnet_59208,
  title = {{XLNet: Generalized Autoregressive Pretraining for Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13223},
}

@inproceedings{neurips2019_unified_59140,
  title = {{Unified Language Model Pre-training for Natural Language Understanding and Generation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14249},
}

@inproceedings{icml2019_mass_37524,
  title = {{MASS: Masked Sequence to Sequence Pre-training for Language Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3802},
}

@inproceedings{iclr2023_glm_31878,
  title = {{GLM-130B: An Open Bilingual Pre-trained Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11329},
}

@inproceedings{iclr2023_large_32153,
  title = {{Large Language Models are Human-Level Prompt Engineers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10850},
}

@inproceedings{iclr2023_quantifying_32639,
  title = {{Quantifying Memorization Across Neural Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11469},
}

@inproceedings{neurips2023_din_69483,
  title = {{DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70430},
}

@inproceedings{neurips2021_coco_63212,
  title = {{COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27099},
}

@inproceedings{icml2023_large_42027,
  title = {{Large Language Models Can Be Easily Distracted by Irrelevant Context}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24255},
}

@inproceedings{iclr2023_ul2_32089,
  title = {{UL2: Unifying Language Learning Paradigms}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10748},
}

@inproceedings{iclr2022_tapex_31213,
  title = {{TAPEX: Table Pre-training via Learning a Neural SQL Executor}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6280},
}

@inproceedings{aaai2020_rare_103093,
  title = {{Rare Words: A Major Problem for Contextualized Embeddings and How to Fix it by Attentive Mimicking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6403},
}

@inproceedings{iclr2018_breaking_28553,
  title = {{Breaking the Softmax Bottleneck: A High-Rank RNN Language Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/70},
}

@inproceedings{icml2022_black_40292,
  title = {{Black-Box Tuning for Language-Model-as-a-Service}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17783},
}

@inproceedings{iclr2024_a_34388,
  title = {{A Simple and Effective Pruning Approach for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18687},
}

@inproceedings{iclr2019_representation_29056,
  title = {{Representation Degeneration Problem in Training Natural Language Generation Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/759},
}

@inproceedings{cvpr2024_llafs_23897,
  title = {{LLaFS: When Large Language Models Meet Few-Shot Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30546},
}

@inproceedings{iclr2020_are_29435,
  title = {{Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=H1xPR3NtPB},
}

@inproceedings{iclr2024_language_35076,
  title = {{Language Modeling Is Compression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17997},
}

@inproceedings{iclr2024_plug_34525,
  title = {{Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18549},
}

@inproceedings{cvpr2024_language_23919,
  title = {{Language Models as Black-Box Optimizers for Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30073},
}

@inproceedings{neurips2024_routerdc_70669,
  title = {{RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96453},
}

@inproceedings{neurips2024_maskllm_71713,
  title = {{MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95573},
}

@inproceedings{aaai2025_selective_10712,
  title = {{Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32068},
}

@inproceedings{neurips2024_algorithmic_70548,
  title = {{Algorithmic progress in language models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96565},
}

@inproceedings{icml2024_mobilellm_43862,
  title = {{MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34590},
}

@inproceedings{neurips2024_sparsellm_73894,
  title = {{SparseLLM: Towards Global Pruning of Pre-trained Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93617},
}

@inproceedings{aaai2024_omnipotent_6820,
  title = {{Omnipotent Distillation with LLMs for Weakly-Supervised Natural Language Video Localization: When Divergence Meets Consistency}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27832},
}

@inproceedings{aaai2024_separate_7318,
  title = {{Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29784},
}

@inproceedings{neurips2024_glbench_70117,
  title = {{GLBench: A Comprehensive Benchmark for Graph with Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97881},
}

@inproceedings{neurips2024_datacomp_71065,
  title = {{DataComp-LM: In search of the next generation of training sets for language models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97814},
}

@inproceedings{iclr2024_silo_35398,
  title = {{SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17675},
}

@inproceedings{icml2024_openmoe_43307,
  title = {{OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35145},
}

@inproceedings{iclr2024_large_35485,
  title = {{Large Language Models as Generalizable Policies for Embodied Tasks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17588},
}

@inproceedings{neurips2024_scaling_73439,
  title = {{Scaling Retrieval-Based Language Models with a Trillion-Token Datastore}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94024},
}

@inproceedings{iclr2024_pb_33868,
  title = {{PB-LLM: Partially Binarized Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19207},
}