% Key papers for Language model pretraining and induction (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_language_36240,
  title = {{Language Modeling with Gated Convolutional Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/887},
}

@inproceedings{aaai2017_summarunner_105809,
  title = {{SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10958},
}

@inproceedings{iclr2021_deberta_30395,
  title = {{DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://openreview.net/forum?id=XPZIaotutsD},
}

@inproceedings{iclr2020_electra_29770,
  title = {{ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=r1xMH1BtvB},
}

@inproceedings{iclr2017_pointer_28240,
  title = {{Pointer Sentinel Mixture Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=Byj72udxe},
}

@inproceedings{aaai2016_a_105188,
  title = {{A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10342},
}

@inproceedings{iclr2021_rethinking_29945,
  title = {{Rethinking Positional Encoding in Language Pre-training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2982},
}

@inproceedings{iclr2021_graphcodebert_30564,
  title = {{GraphCodeBERT: Pre-training Code Representations with Data Flow}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2598},
}

@inproceedings{aaai2018_search_105953,
  title = {{Search Engine Guided Neural Machine Translation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12013},
}

@inproceedings{iclr2019_what_29052,
  title = {{What do you learn from context? Probing for sentence structure in contextualized word representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1009},
}

@inproceedings{neurips2020_investigating_60112,
  title = {{Investigating Gender Bias in Language Models Using Causal Mediation Analysis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17994},
}

@inproceedings{aaai2021_contrastive_323,
  title = {{Contrastive Triple Extraction with Generative Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/14257-contrastive-triple-extraction-with-generative-transformer/},
}

@inproceedings{iclr2020_pre_29830,
  title = {{Pre-training Tasks for Embedding-based Large-scale Retrieval}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rkg-mA4FDr},
}

@inproceedings{aaai2020_lexical_103079,
  title = {{Lexical Simplification with Pretrained Encoders}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6389},
}

@inproceedings{aaai2020_keywords_103023,
  title = {{Keywords-Guided Abstractive Sentence Summarization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6333},
}

@inproceedings{aaai2018_syntax_105812,
  title = {{Syntax-Directed Attention for Neural Machine Translation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11910},
}

@inproceedings{aaai2021_rethinking_1272,
  title = {{Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12785-rethinking-boundaries-end-to-end-recognition-of-discontinuous-mentions-with-pointer-networks/},
}

@inproceedings{iclr2019_adaptive_28854,
  title = {{Adaptive Input Representations for Neural Language Modeling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/950},
}

@inproceedings{iclr2021_on_30629,
  title = {{On Position Embeddings in BERT}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3249},
}

@inproceedings{aaai2020_guiding_102949,
  title = {{Guiding Attention in Sequence-to-Sequence Models for Dialogue Act Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6259},
}

@inproceedings{neurips2024_the_74037,
  title = {{The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93487},
}

@inproceedings{cvpr2025_pact_27173,
  title = {{PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32558},
}

@inproceedings{icml2024_the_43559,
  title = {{The Pitfalls of Next-Token Prediction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34893},
}

@inproceedings{neurips2024_spacebyte_71594,
  title = {{SpaceByte: Towards Deleting Tokenization from Large Language Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95677},
}

@inproceedings{aaai2024_layer_6432,
  title = {{Layer-Wise Representation Fusion for Compositional Generalization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29944},
}

@inproceedings{iclr2024_test_33899,
  title = {{Test-Time Training on Nearest Neighbors for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19176},
}

@inproceedings{cvpr2024_predtoken_24507,
  title = {{PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29183},
}

@inproceedings{iclr2024_headless_34331,
  title = {{Headless Language Models: Learning without Predicting with Contrastive Weight Tying}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18744},
}

@inproceedings{icml2024_progressive_45058,
  title = {{Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33394},
}

@inproceedings{icml2026_progressive_49718,
  title = {{Progressive Cramming: Reliable Token Compression and What It Reveals}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=55jIiEADcf},
}

@inproceedings{icml2026_end_50008,
  title = {{End-to-End Compression for Tabular Foundation Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=84mfkGDxYh},
}

@inproceedings{icml2026_separating_51552,
  title = {{Separating Representation from Reconstruction Enables Scalable Text Encoders}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=NVMMpdARqa},
}

@inproceedings{icml2026_proxy_53295,
  title = {{Proxy Compression for Language Modeling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=e41bikBTnV},
}

@inproceedings{icml2026_the_53737,
  title = {{The Efficiency Gap in Byte Modeling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=iD5JNtPwGA},
}

@inproceedings{icml2026_hyprag_55149,
  title = {{HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=w6FXg6d6My},
}

@inproceedings{neurips2025_explaining_74729,
  title = {{Explaining and Mitigating Crosslingual Tokenizer Inequities}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0Y7AxxNCYh},
}

@inproceedings{neurips2025_unifying_76087,
  title = {{Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=FIfjDqjV0B},
}

@inproceedings{neurips2025_order_77456,
  title = {{Order-Level Attention Similarity Across Language Models: A Latent Commonality}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=U0WEtpp6kO},
}

@inproceedings{neurips2025_blockdecoder_78213,
  title = {{BlockDecoder: Boosting ASR Decoders with Context and Merger Modules}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=cGmcHJEFnY},
}

@inproceedings{neurips2025_beast_79639,
  title = {{BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=rQCl1sf62w},
}