Differences

This shows you the differences between two versions of the page.

--- ml:state-space_models [2024/04/30 08:43] – [Key Papers] jmflanig
+++ ml:state-space_models [2025/08/22 17:58] (current) – [Key Papers] jmflanig
@@ Line 2: / Line 2: @@
 ===== Overviews =====
-  * [[https://arxiv.org/pdf/2008.07669.pdf|Gu et al 2020 - HiPPO: Recurrent Memory with Optimal Polynomial Projections]]
+  * **Survey Papers**
-  * S4 model: **[[https://arxiv.org/pdf/2111.00396.pdf|Gu et al 2021 - Efficiently Modeling Long Sequences with Structured State Spaces]]** Good intro to state spaces
+    * [[https://arxiv.org/pdf/2404.16112|2024 - Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modeling: Methods, Applications, and Challenges]]
-  * [[https://arxiv.org/pdf/2303.06349.pdf|Orvieto et al 2023 - Resurrecting Recurrent Neural Networks for Long Sequences]]
+  * **Papers with Good Overviews**
-  * **[[https://arxiv.org/pdf/2312.00752.pdf|Gu & Dao 2023 - Mamba: Linear-Time Sequence Modeling with Selective State Spaces]]** Nice overview of SSMs
+    * [[https://arxiv.org/pdf/2008.07669.pdf|Gu et al 2020 - HiPPO: Recurrent Memory with Optimal Polynomial Projections]]
+    * S4 model: **[[https://arxiv.org/pdf/2111.00396.pdf|Gu et al 2021 - Efficiently Modeling Long Sequences with Structured State Spaces]]** Good intro to state spaces
+    * [[https://arxiv.org/pdf/2303.06349.pdf|Orvieto et al 2023 - Resurrecting Recurrent Neural Networks for Long Sequences]]
+    * **[[https://arxiv.org/pdf/2312.00752.pdf|Gu & Dao 2023 - Mamba: Linear-Time Sequence Modeling with Selective State Spaces]]** Nice overview of SSMs
 ===== Key Papers =====
@@ Line 18: / Line 21: @@
   * [[https://arxiv.org/pdf/2307.08621.pdf|Sun et al 2023 - Retentive Network: A Successor to Transformer
 for Large Language Models]]
-  * [[https://arxiv.org/pdf/2312.00752.pdf|Gu & Dao 2023 - Mamba: Linear-Time Sequence Modeling with Selective State Spaces]]
+  * [[https://arxiv.org/pdf/2312.00752.pdf|Gu & Dao 2023 - Mamba: Linear-Time Sequence Modeling with Selective State Spaces]] First rejected at [[https://openreview.net/forum?id=AL1fq05o7H|ICLR]] (bad reviewing) and then accepted to COLM ([[https://openreview.net/forum?id=tEYskw1VY2#discussion|reviews]])
+    * [[https://srush.github.io/annotated-mamba/hard.html|Mamba: The Hard Way]] Sasha Rush's tutorial implementation
+    * [[https://github.com/sustcsonglin/mamba-triton/tree/master]]
   * [[https://arxiv.org/pdf/2401.13660.pdf|Wang et al 2024 - MambaByte: Token-free Selective State Space Model]]
+  * [[https://arxiv.org/pdf/2402.19427|De et al 2024 - Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models]]
   * [[https://arxiv.org/pdf/2403.01590|Ali et al 2024 - The Hidden Attention of Mamba Models]]
+  * [[https://arxiv.org/pdf/2403.19887|Leiber et al 2024 - Jamba: A Hybrid Transformer-Mamba Language Model]]
+  * [[https://arxiv.org/pdf/2405.21060|Dao & Gu 2024 - Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality]]
+  * [[https://arxiv.org/pdf/2408.10189|Bick et al 2024 - Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models]]
 ===== Papers =====
   * [[https://arxiv.org/pdf/2304.12776.pdf|Vardasbi et al 2023 - State Spaces Aren’t Enough: Machine Translation Needs Attention]]
+===== Analysis and Mechanistic Interpretability =====
+  * [[https://arxiv.org/pdf/2404.03646|Sharma et al 2024 - Locating and Editing Factual Associations in Mamba]]
+  * [[https://arxiv.org/pdf/2505.24244|Endy et al 2025 - Mamba Knockout for Unraveling Factual Information Flow]]
+===== Theoretical Properties =====
+  * [[https://arxiv.org/pdf/2404.08819|Merrill et al 2024 - The Illusion of State in State-Space Models]]
 ===== People =====
+  * [[https://scholar.google.com/citations?user=NQRw0bQAAAAJ&hl=en|Tri Dao]]
   * [[https://scholar.google.com/citations?user=DVCHv1kAAAAJ&hl=en|Albert Gu]]