% Key papers for Long-context KV and memory attention (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2017_a_28216,
  title = {{A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=BJC_jUqxe},
}

@inproceedings{neurips2020_minilm_60315,
  title = {{MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17311},
}

@inproceedings{iclr2018_qanet_28396,
  title = {{QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://openreview.net/forum?id=B14TlG-RW},
}

@inproceedings{aaai2018_deep_105830,
  title = {{Deep Semantic Role Labeling With Self-Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11928},
}

@inproceedings{aaai2021_dialogxl_424,
  title = {{DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13789-dialogxl-all-in-one-xlnet-for-multi-party-conversation-emotion-recognition/},
}

@inproceedings{aaai2020_copymtl_103185,
  title = {{CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6495},
}

@inproceedings{aaai2020_sg_103201,
  title = {{SG-Net: Syntax-Guided Machine Reading Comprehension}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6511},
}

@inproceedings{aaai2020_interpretable_103095,
  title = {{Interpretable Rumor Detection in Microblogs by Attending to User Interactions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6405},
}

@inproceedings{aaai2021_entity_531,
  title = {{Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/14149-entity-structure-within-and-throughout-modeling-mention-dependencies-for-document-level-relation-extraction/},
}

@inproceedings{cvpr2020_scatter_16152,
  title = {{SCATTER: Selective Context Attentional Scene Text Recognizer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2020_convbert_59597,
  title = {{ConvBERT: Improving BERT with Span-based Dynamic Convolution}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16831},
}

@inproceedings{aaai2018_event_105821,
  title = {{Event Detection via Gated Multilingual Attention Mechanism}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11919},
}

@inproceedings{iclr2018_dcn_28498,
  title = {{DCN+: Mixed Objective And Deep Residual Coattention for Question Answering}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/258},
}

@inproceedings{iclr2020_monotonic_29547,
  title = {{Monotonic Multihead Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=Hyg96gBKPS},
}

@inproceedings{aaai2021_bridging_214,
  title = {{Bridging Towers of Multi-task Learning with a Gating Mechanism for Aspect-based Sentiment Analysis and Sequential Metaphor Identification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13534-bridging-towers-of-multi-task-learning-with-a-gating-mechanism-for-aspect-based-sentiment-analysis-and-sequential-metaphor-identification/},
}

@inproceedings{aaai2021_context_308,
  title = {{Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/14094-context-guided-bert-for-targeted-aspect-based-sentiment-analysis/},
}

@inproceedings{aaai2020_self_103032,
  title = {{Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6342},
}

@inproceedings{neurips2022_squeezeformer_65640,
  title = {{Squeezeformer: An Efficient Transformer for Automatic Speech Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54855},
}

@inproceedings{aaai2020_deep_103013,
  title = {{Deep Attentive Ranking Networks for Learning to Order Sentences}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6323},
}

@inproceedings{icml2022_branchformer_40299,
  title = {{Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18225},
}

@inproceedings{cvpr2024_low_24035,
  title = {{Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30084},
}

@inproceedings{neurips2025_gated_74825,
  title = {{Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1b7whO4SfY},
}

@inproceedings{aaai2024_arithmetic_5208,
  title = {{Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29033},
}

@inproceedings{neurips2024_arkvale_70473,
  title = {{ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96635},
}

@inproceedings{iclr2025_tabm_82201,
  title = {{TabM: Advancing tabular deep learning with parameter-efficient ensembling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29590},
}

@inproceedings{aaai2024_fast_5975,
  title = {{Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30480},
}

@inproceedings{iclr2024_compressed_33671,
  title = {{Compressed Context Memory for Online Language Model Interaction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19404},
}

@inproceedings{iclr2024_zoology_34215,
  title = {{Zoology: Measuring and Improving Recall in Efficient Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18860},
}

@inproceedings{icml2024_from_43556,
  title = {{From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34896},
}

@inproceedings{aaai2025_bert_8210,
  title = {{BERT-Based Code Learning for Exception Localization and Type Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32090},
}

@inproceedings{iclr2024_masked_34392,
  title = {{Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18683},
}

@inproceedings{icml2024_dijiang_43278,
  title = {{DiJiang: Efficient Large Language Models through Compact Kernelization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35174},
}

@inproceedings{icml2025_gumiho_45857,
  title = {{Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46686},
}

@inproceedings{icml2025_tabflex_47956,
  title = {{TabFlex: Scaling Tabular Learning to Millions with Linear Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44649},
}

@inproceedings{icml2025_catekv_48879,
  title = {{CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43744},
}

@inproceedings{icml2026_the_51914,
  title = {{The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=R49Bwg8WZ6},
}

@inproceedings{icml2026_sparse_52224,
  title = {{(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Trfut9gSjY},
}

@inproceedings{icml2026_limix_52749,
  title = {{LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=YjYPYg112A},
}

@inproceedings{icml2026_dustin_52782,
  title = {{Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Z1Ju4QIZmg},
}

@inproceedings{icml2026_meg_53159,
  title = {{MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=cefix4VmhS},
}