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

@inproceedings{cvpr2020_meshed_15881,
  title = {{Meshed-Memory Transformer for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{icml2022_improving_40688,
  title = {{Improving Language Models by Retrieving from Trillions of Tokens}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17479},
}

@inproceedings{cvpr2024_momask_24162,
  title = {{MoMask: Generative Masked Modeling of 3D Human Motions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29638},
}

@inproceedings{aaai2020_treegen_103120,
  title = {{TreeGen: A Tree-Based Transformer Architecture for Code Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6430},
}

@inproceedings{iclr2020_lite_29361,
  title = {{Lite Transformer with Long-Short Range Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=ByeMPlHKPH},
}

@inproceedings{icml2019_insertion_37453,
  title = {{Insertion Transformer: Flexible Sequence Generation via Insertion Operations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4221},
}

@inproceedings{neurips2018_layer_57270,
  title = {{Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11762},
}

@inproceedings{cvpr2020_sign_16241,
  title = {{Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2018_tree_57733,
  title = {{Tree-to-tree Neural Networks for Program Translation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11263},
}

@inproceedings{iclr2022_charformer_31137,
  title = {{Charformer: Fast Character Transformers via Gradient-based Subword Tokenization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6303},
}

@inproceedings{icml2020_non_38513,
  title = {{Non-autoregressive Machine Translation with Disentangled Context Transformer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5827},
}

@inproceedings{aaai2019_tied_101772,
  title = {{Tied Transformers: Neural Machine Translation with Shared Encoder and Decoder}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4487},
}

@inproceedings{iclr2023_mass_32454,
  title = {{Mass-Editing Memory in a Transformer}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11880},
}

@inproceedings{iclr2021_share_30386,
  title = {{Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3193},
}

@inproceedings{iclr2020_improving_29391,
  title = {{Improving Neural Language Generation with Spectrum Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=ByxY8CNtvr},
}

@inproceedings{aaai2020_alignment_103108,
  title = {{Alignment-Enhanced Transformer for Constraining NMT with Pre-Specified Translations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6418},
}

@inproceedings{aaai2019_dynamic_99679,
  title = {{Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3772},
}

@inproceedings{iclr2022_memorizing_31323,
  title = {{Memorizing Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6064},
}

@inproceedings{neurips2020_accelerating_59308,
  title = {{Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16943},
}

@inproceedings{icml2021_terapipe_40010,
  title = {{TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9181},
}

@inproceedings{iclr2024_zipformer_33783,
  title = {{Zipformer: A faster and better encoder for automatic speech recognition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19292},
}

@inproceedings{aaai2025_tamer_10894,
  title = {{TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33190},
}

@inproceedings{neurips2024_fastopic_70708,
  title = {{FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96416},
}

@inproceedings{neurips2024_deepstack_73236,
  title = {{DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94201},
}

@inproceedings{neurips2024_magnet_70229,
  title = {{MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96857},
}

@inproceedings{iclr2024_clam_35265,
  title = {{CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17808},
}

@inproceedings{neurips2024_aligner_74159,
  title = {{Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93383},
}

@inproceedings{neurips2025_ffn_77783,
  title = {{FFN Fusion: Rethinking Sequential Computation in Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=XUmGMBRv4M},
}

@inproceedings{aaai2025_linear_9797,
  title = {{Linear Decoding of Morphology Relations in Language Models (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35315},
}

@inproceedings{iclr2024_augmenting_35487,
  title = {{Augmenting Transformers with Recursively Composed Multi-grained Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17586},
}

@inproceedings{icml2024_transformers_43367,
  title = {{Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35085},
}

@inproceedings{icml2024_stablemask_43944,
  title = {{StableMask: Refining Causal Masking in Decoder-only Transformer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34508},
}

@inproceedings{icml2024_how_45207,
  title = {{How do Transformers Perform In-Context Autoregressive Learning ?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33245},
}

@inproceedings{icml2025_overcoming_46805,
  title = {{Overcoming Non-monotonicity in Transducer-based Streaming Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45770},
}

@inproceedings{icml2026_xspecmesh_49447,
  title = {{XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=2eKOeHaNZG},
}

@inproceedings{icml2026_focus_49596,
  title = {{FOCUS: DLLMs Know How to Tame Their Compute Bound}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=40fUEdwvH3},
}

@inproceedings{icml2026_prototype_50637,
  title = {{Prototype Transformer: Towards Language Model Architectures Interpretable by Design}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ELiOhFJIPh},
}

@inproceedings{icml2026_thoughtbubbles_51380,
  title = {{Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Lc6I5LvHGw},
}

@inproceedings{icml2026_fast_51647,
  title = {{Fast and Accurate Causal Parallel Decoding using Jacobi Forcing}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ORy2hyPd4G},
}