References

Every paper, book, and software citation in this guide, sorted alphabetically by first-author surname. Click an entry's anchor to share a deep link, or follow the arXiv / DOI / URL for the source.

66 entries. Generated from guides/shared/references.bib at build time via scripts/build-bib.mjs.

  1. [arxiv241112537] Anonymous (2024). Were RNNs All We Needed? A Study of Linear RNNs with Negative Eigenvalues.
  2. [arxiv240516504] Anonymous (2024). Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation.
  3. [mamba_lyapunov_tmlr] Anonymous (2025). Lyapunov Stability Analysis of Mamba. Transactions on Machine Learning Research (TMLR).
  4. [arxiv250612810] Anonymous (2025). Lyapunov Exponents as a Training Signal for Edge-of-Chaos Neural Networks.
  5. [arxiv250808435] Anonymous (2025). Fast Weight Programmers and Linear Transformers: A Unified Survey.
  6. [arxiv251004944] Anonymous (2025). On Structured State-Space Duality.
  7. [arxiv251002228] Anonymous (2025). Scaling Laws for Linear Recurrent Architectures.
  8. [arxiv250515105] Anonymous (2025). Mechanistic Evaluation of Linear-Recurrence Architectures.
  9. [arxiv151106464] Martin Arjovsky, Amar Shah, and Yoshua Bengio (2015). Unitary Evolution Recurrent Neural Networks.
  10. [arora2024zoology] Simran Arora, Sabri Eyuboglu, Aman Timalsina, Isys Johnson, Michael Poli, James Zou, Atri Rudra, and Christopher Ré (2024). Zoology: Measuring and Improving Recall in Efficient Language Models.
  11. [arora2024based] Simran Arora, Sabri Eyuboglu, Michael Zhang, Aman Timalsina, Silas Alberti, Dylan Halpern, James Zou, Atri Rudra, and Christopher Ré (2024). Simple Linear Attention Language Models Balance the Recall-Throughput Tradeoff.
  12. [arora2025mechanistic] Aryaman Arora, Neil Rathi, Nikil Roashan Selvam, Róbert Csordás, Dan Jurafsky, and Christopher Potts (2025). Mechanistic Evaluation of Transformers and State Space Models.
  13. [arora2025recall] Aryaman Arora and others (2025). When Recalling In-Context, Transformers are Not SSMs.
  14. [beck2024xlstm] Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksii Prudnikov, Michael Kopp, Günter Klambauer, Johannes Brandstetter, and Sepp Hochreiter (2024). xLSTM: Extended Long Short-Term Memory.
  15. [nxai2025xlstm7b] Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Curto, Patrick Blies, Günter Klambauer, Johannes Brandstetter, and Sepp Hochreiter (2025). xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference.
  16. [benettin1980lyapunov] Giancarlo Benettin, Luigi Galgani, Antonio Giorgilli, and Jean-Marie Strelcyn (1980). Lyapunov characteristic exponents for smooth dynamical systems and for Hamiltonian systems; a method for computing all of them. Meccanica. Vol. 15, no. 1. pp. 9-20.
  17. [bick2025gather] Aviv Bick, Eric Xing, and Albert Gu (2025). Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism. ICML.
  18. [blelloch1990prefix] Guy E. Blelloch (1990). Prefix sums and their applications. Synthesis of Parallel Algorithms. pp. 35-60.
  19. [jax2018] James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang (2018). JAX: Composable transformations of Python+NumPy programs. link.
  20. [arxiv180607366] Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud (2018). Neural Ordinary Differential Equations.
  21. [chen2025achilles] Chen, Lin, Wang, and Xu (2025). Achilles' Heel of Mamba. NeurIPS Spotlight.
  22. [arxiv220514135] Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, and Christopher Ré (2022). FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.
  23. [dao2024mamba2] Tri Dao and Albert Gu (2024). Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality. International Conference on Machine Learning (ICML). link.
  24. [arxiv240521060] Tri Dao and Albert Gu (2024). Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.
  25. [arxiv200602427] Rainer Engelken, Fred Wolf, and L. F. Abbott (2020). Lyapunov spectra of chaotic recurrent neural networks.
  26. [arxiv150304069] Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, and Jürgen Schmidhuber (2015). LSTM: A Search Space Odyssey.
  27. [arxiv190601563] Sam Greydanus, Misko Dzamba, and Jason Yosinski (2019). Hamiltonian Neural Networks.
  28. [gu2020hippo] Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, and Christopher Ré (2020). HiPPO: Recurrent Memory with Optimal Polynomial Projections. Advances in Neural Information Processing Systems (NeurIPS). link.
  29. [arxiv200807669] Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, and Christopher Re (2020). HiPPO: Recurrent Memory with Optimal Polynomial Projections.
  30. [arxiv211013985] Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and others (2021). Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers.
  31. [arxiv211100396] Albert Gu, Karan Goel, and Christopher Ré (2021). Efficiently Modeling Long Sequences with Structured State Spaces.
  32. [gu2022s4] Albert Gu, Karan Goel, and Christopher Ré (2022). Efficiently Modeling Long Sequences with Structured State Spaces. International Conference on Learning Representations (ICLR). link.
  33. [gu2022s4d] Albert Gu, Ankit Gupta, Karan Goel, and Christopher Ré (2022). On the Parameterization and Initialization of Diagonal State Space Models. Advances in Neural Information Processing Systems (NeurIPS). link.
  34. [arxiv220611893] Albert Gu, Ankit Gupta, Karan Goel, and Christopher Ré (2022). On the Parameterization and Initialization of Diagonal State Space Models.
  35. [arxiv220612037] Albert Gu, Isys Johnson, Aman Timalsina, Atri Rudra, and Christopher Ré (2022). How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections.
  36. [gu2024mamba] Albert Gu and Tri Dao (2024). Mamba: Linear-Time Sequence Modeling with Selective State Spaces. International Conference on Machine Learning (ICML). link.
  37. [gu2025mamba3] Albert Gu, Tri Dao, and Naman Vyas (2025). Mamba-3: Improved Sequence Modeling using State Space Principles. link.
  38. [gupta2022diagonal] Ankit Gupta, Albert Gu, and Jonathan Berant (2022). Diagonal State Spaces Are As Effective As Dense State Spaces. Advances in Neural Information Processing Systems (NeurIPS). link.
  39. [arxiv220314343] Ankit Gupta, Albert Gu, and Jonathan Berant (2022). Diagonal State Spaces are as Effective as Structured State Spaces.
  40. [hairer1996solving] Ernst Hairer and Gerhard Wanner (1996). Solving Ordinary Differential Equations II: Stiff and Differential-Algebraic Problems. Springer-Verlag. Vol. 14.
  41. [arxiv240201032] Samy Jelassi, David Brandfonbrener, Sham M. Kakade, and Eran Malach (2024). Repeat After Me: Transformers are Better than State Space Models at Copying.
  42. [jelassi2024repeat] Samy Jelassi, David Brandfonbrener, Sham M. Kakade, and Eran Malach (2024). Repeat After Me: Transformers are Better than State Space Models at Copying.
  43. [arxiv200616236] Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and François Fleuret (2020). Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention.
  44. [arxiv260315569] Aakash Lahoti, Kevin Y. Li, Berlin Chen, Caitlin Wang, Aviv Bick, J. Zico Kolter, and others (2026). Mamba-3: Improved Sequence Modeling using State Space Principles.
  45. [liu2024longhorn] Bo Liu, Rui Wang, Lemeng Wu, Yihao Feng, Peter Stone, and Qiang Liu (2024). Longhorn: State Space Models are Amortized Online Learners.
  46. [merrill2024illusion] William Merrill and Ashish Sabharwal (2024). The Illusion of State in State-Space Models. International Conference on Machine Learning (ICML). link.
  47. [orvieto2023resurrecting] Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Caglar Gulcehre, Razvan Pascanu, and Soham De (2023). Resurrecting Recurrent Neural Networks for Long Sequences. International Conference on Machine Learning (ICML). link.
  48. [arxiv12115063] Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio (2012). On the difficulty of training Recurrent Neural Networks.
  49. [peng2025rwkv] Bo Peng, Daniel Goldstein, Quentin Anthony, Alon Albalak, Eric Alcaide, Stella Biderman, and others (2024). Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence.
  50. [peng2025rwkv7] Bo Peng and others (2025). RWKV-7 “Goose” with Expressive Dynamic State Evolution.
  51. [poli2023hyena] Michael Poli, Stefano Massaroli, Eric Nguyen, Daniel Y. Fu, Tri Dao, Stephen Baccus, Yoshua Bengio, Stefano Ermon, and Christopher Ré (2023). Hyena Hierarchy: Towards Larger Convolutional Language Models. International Conference on Machine Learning (ICML). link.
  52. [qin2024hgrn2] Zhen Qin, Songlin Yang, Weixuan Sun, Xuyang Shen, Dong Li, Weigao Sun, and Yiran Zhong (2024). HGRN2: Gated Linear RNNs with State Expansion.
  53. [arxiv13126120] Andrew M. Saxe, James L. McClelland, and Surya Ganguli (2013). Exact solutions to the nonlinear dynamics of learning in deep linear neural networks.
  54. [arxiv210211174] Imanol Schlag, Kazuki Irie, and Jürgen Schmidhuber (2021). Linear Transformers Are Secretly Fast Weight Programmers.
  55. [smith2023s5] Jimmy T.H. Smith, Andrew Warrington, and Scott W. Linderman (2023). Simplified State Space Layers for Sequence Modeling. International Conference on Learning Representations (ICLR). link.
  56. [sun2023retnet] Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqing Xia, Jilong Xue, Jianyong Wang, and Furu Wei (2023). Retentive Network: A Successor to Transformer for Large Language Models.
  57. [arxiv201104006] Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, and others (2020). Long Range Arena: A Benchmark for Efficient Transformers.
  58. [kimi2025linear] Kimi Team (2025). Kimi Linear: An Expressive, Efficient Attention Architecture.
  59. [arxiv170509792] Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, João Felipe Santos, and others (2017). Deep Complex Networks.
  60. [arxiv170603762] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, and others (2017). Attention Is All You Need.
  61. [arxiv210613008] Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long (2021). Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting.
  62. [arxiv231206635] Songlin Yang, Bailin Wang, Yikang Shen, Rameswar Panda, and Yoon Kim (2023). Gated Linear Attention Transformers with Hardware-Efficient Training.
  63. [arxiv241206464] Songlin Yang, Jan Kautz, and Ali Hatamizadeh (2024). Gated Delta Networks: Improving Mamba2 with Delta Rule.
  64. [yang2024gated] Songlin Yang, Jan Kautz, and Ali Hatamizadeh (2024). Gated Delta Networks: Improving Mamba2 with Delta Rule.
  65. [yang2024deltanet] Songlin Yang, Bailin Wang, Yu Zhang, Yikang Shen, and Yoon Kim (2024). Parallelizing Linear Transformers with the Delta Rule over Sequence Length.
  66. [arxiv201207436] Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, Jianxin Li, Hui Xiong, and others (2020). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting.