@article{vaswani2017attention,
  title   = {Attention Is All You Need},
  author  = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, Lukasz and Polosukhin, Illia},
  journal = {Advances in Neural Information Processing Systems},
  volume  = {30},
  year    = {2017},
  url     = {https://arxiv.org/abs/1706.03762}
}

@inproceedings{devlin2019bert,
  title     = {BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
  author    = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  booktitle = {Proceedings of NAACL-HLT},
  pages     = {4171--4186},
  year      = {2019},
  url       = {https://arxiv.org/abs/1810.04805}
}

@misc{github_honkit,
  title        = {HonKit: Building beautiful books using Markdown},
  author       = {{HonKit Contributors}},
  year         = {2024},
  howpublished = {\url{https://github.com/honkit/honkit}},
  note         = {Accessed: 2026-09-14}
}

@online{mdn_fetch,
  title   = {Using the Fetch API},
  author  = {{MDN Web Docs}},
  year    = {2025},
  url     = {https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API/Using_Fetch},
  urldate = {2026-09-14}
}

@inproceedings{katharopoulos2020transformers,
  title     = {Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention},
  author    = {Katharopoulos, Angelos and Vyas, Apoorv and Pappas, Nikolaos and Fleuret, Fran{\c{c}}ois},
  booktitle = {Proceedings of the 37th International Conference on Machine Learning (ICML)},
  year      = {2020},
  url       = {https://arxiv.org/abs/2006.16236}
}

@article{gu2023mamba,
  title   = {Mamba: Linear-Time Sequence Modeling with Selective State Spaces},
  author  = {Gu, Albert and Dao, Tri},
  journal = {arXiv preprint arXiv:2312.00752},
  year    = {2023},
  url     = {https://arxiv.org/abs/2312.00752}
}

@inproceedings{schlag2021linear,
  title     = {Linear Transformers Are Secretly Fast Weight Programmers},
  author    = {Schlag, Imanol and Irie, Kazuki and Schmidhuber, J{\"u}rgen},
  booktitle = {Proceedings of the 38th International Conference on Machine Learning (ICML)},
  year      = {2021},
  url       = {https://arxiv.org/abs/2102.11174}
}

@article{widrow1960adaptive,
  title   = {Adaptive Switching Circuits},
  author  = {Widrow, Bernard and Hoff, Marcian E.},
  journal = {IRE WESCON Convention Record},
  year    = {1960},
  url     = {https://isl.stanford.edu/~widrow/papers/c1960adaptiveswitching.pdf}
}

@inproceedings{bischof1985wy,
  title     = {The {WY} Representation for Products of Householder Matrices},
  author    = {Bischof, Christian H. and Van Loan, Charles},
  booktitle = {SIAM Conference on Parallel Processing for Scientific Computing},
  year      = {1985},
  url       = {https://api.semanticscholar.org/CorpusID:36094006}
}

@inproceedings{grazzi2024unlocking,
  title     = {Unlocking State-Tracking in Linear {RNNs} Through Negative Eigenvalues},
  author    = {Grazzi, Riccardo and Siems, Julien and Zela, Arber and Franke, J{\"o}rg K. H. and Hutter, Frank and Pontil, Massimiliano},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2025},
  url       = {https://arxiv.org/abs/2411.12537}
}

@inproceedings{dao2024transformers,
  title     = {Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality},
  author    = {Dao, Tri and Gu, Albert},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)},
  year      = {2024},
  url       = {https://arxiv.org/abs/2405.21060}
}

@inproceedings{yang2024parallelizing,
  title     = {Parallelizing Linear Transformers with the Delta Rule over Sequence Length},
  author    = {Yang, Songlin and Wang, Bailin and Zhang, Yu and Shen, Yikang and Kim, Yoon},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2024},
  url       = {https://arxiv.org/abs/2406.06484}
}

@inproceedings{yang2024gla,
  title     = {Gated Linear Attention Transformers with Hardware-Efficient Training},
  author    = {Yang, Songlin and Wang, Bailin and Shen, Yikang and Panda, Rameswar and Kim, Yoon},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)},
  year      = {2024},
  url       = {https://arxiv.org/abs/2312.06635}
}

@article{han2024demystify,
  title   = {Demystify Mamba in Vision: A Linear Attention Perspective},
  author  = {Han, Dongchen and Wang, Zhendong and Xia, Zhuofan and Han, Yizeng and Pu, Yifan and Ge, Chunjiang and Song, Jun and Tong, Yun and Liao, Jianxin and Zhang, Jiangning and Liu, Xihui and Guo, Baining and Huang, Gao},
  journal = {arXiv preprint arXiv:2405.16605},
  year    = {2024},
  url     = {https://arxiv.org/abs/2405.16605}
}

@inproceedings{yang2025gateddelta,
  title     = {Gated Delta Networks: Improving Mamba2 with Delta Rule},
  author    = {Yang, Songlin and Kautz, Jan and Hatamizadeh, Ali},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2025},
  url       = {https://arxiv.org/abs/2412.06464}
}

@inproceedings{liu2024longhorn,
  title     = {Longhorn: State Space Models are Amortized Online Learners},
  author    = {Liu, Bo and Yang, Rui and Wang, Lemeng and Li, Jiawei and Zhang, Qiang and Yang, Songlin and Chen, Yihang and Cao, Yiping and Wang, Wei and Xu, Yi and Srivastava, Nitish and Lu, Chaochao and Zhang, Ce and Liu, Mengdi and Sun, Yutao and Guo, Baining},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2024},
  url       = {https://arxiv.org/abs/2407.14207}
}

@misc{deepseek2026v41flash,
  title        = {DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression},
  author       = {{DeepSeek-AI}},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash}},
  note         = {Accessed: 2026-09-18}
}

@article{cheng2026engram,
  title   = {Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models},
  author  = {Cheng, Xin and Tian, Rui and Zeng, Wangding and Dai, Damai and Chen, Qinyu and Wang, Bingxuan and Xie, Zhenda and Huang, Kezhao and Yu, Xingkai and Deng, Chengqi and Zhou, Shangyan and Zhao, Chenggang and Hao, Zhewen and Li, Yukun and Zhang, Han and Zhang, Zhengyan and Wei, Yixu and Xu, M. Y and Zhang, Huishuai and Zhao, Dongyan and Liang, Wenfeng},
  journal = {arXiv preprint arXiv:2601.07372},
  year    = {2026},
  url     = {https://arxiv.org/abs/2601.07372}
}

@inproceedings{tito2017hashembeddings,
  title     = {Hash Embeddings for Efficient Word Representations},
  author    = {Tito Svenstrup, Dan and Hansen, Jonas Meinertz and Winther, Ole},
  booktitle = {Advances in Neural Information Processing Systems},
  volume    = {30},
  year      = {2017},
  url       = {https://arxiv.org/abs/1709.03933}
}

@misc{github_engram,
  title        = {Engram: Official Implementation of Conditional Memory via Scalable Lookup},
  author       = {{DeepSeek-AI}},
  year         = {2026},
  howpublished = {\url{https://github.com/deepseek-ai/Engram}},
  note         = {Apache-2.0. Accessed: 2026-09-19}
}

@article{li2026userasengram,
  title   = {User as Engram: Internalizing Per-User Memory as Local Parametric Edits},
  author  = {Li, Bojie},
  journal = {arXiv preprint arXiv:2606.19172},
  year    = {2026},
  url     = {https://arxiv.org/abs/2606.19172}
}

@inproceedings{ghandeharioun2024patchscopes,
  title     = {Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models},
  author    = {Ghandeharioun, Asma and Caciularu, Avi and Pearce, Adam and Dixon, Lucas and Geva, Mor},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)},
  pages     = {15466--15490},
  year      = {2024},
  url       = {https://arxiv.org/abs/2401.06102}
}

@inproceedings{zhu2024hyper,
  title     = {Hyper-Connections},
  author    = {Zhu, Defa and Huang, Hongzhi and Huang, Zihao and Zeng, Yutao and Mao, Yunyao and Wu, Banggu and Min, Qiyang and Zhou, Xun},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2025},
  url       = {https://arxiv.org/abs/2409.19606}
}

@article{xie2025mhc,
  title   = {mHC: Manifold-Constrained Hyper-Connections},
  author  = {Xie, Zhenda and Wei, Yixuan and Cao, Huanqi and Zhao, Chenggang and Deng, Chengqi and Li, Jiashi and Dai, Damai and Gao, Huazuo and Chang, Jiang and Yu, Kuai and Zhao, Liang and Zhou, Shangyan and Xu, Zhean and Zhang, Zhengyan and Zeng, Wangding and Hu, Shengding and Wang, Yuqing and Yuan, Jingyang and Wang, Lean and Liang, Wenfeng},
  journal = {arXiv preprint arXiv:2512.24880},
  year    = {2025},
  url     = {https://arxiv.org/abs/2512.24880}
}