Event-AHU/Mamba_State_Space_Model_Paper_List

This GitHub repository is a curated list of academic papers about State Space Models (SSMs) — a class of AI model architectures — and their applications. The collection is maintained by a research team (associated with the Event-AHU GitHub account) and is anchored around their own survey paper, titled "State Space Model for New-Generation Network Alternative to Transformers: A Survey" (2024). The survey's title indicates that SSMs are being explored as a possible successor to the Transformer architecture, which is a widely used building block in modern AI.

The repository is organized into several parts:

• Update log — Tracks milestones, including the release of the survey on arXiv (April 2024), slides (May 2024), and an acceptance of the survey by the journal Visual Intelligence (noted as September 2026 in the log).
• Video tutorial — Links to a recorded talk about "Mamba," a specific SSM method (labeled as a COLM Oral 2024 presentation).
• Thesis & Surveys — Lists other survey papers and a doctoral thesis on SSMs and related topics, each with links to their PDFs or pages (mostly on arXiv).
• Yearly paper lists — Entries for 2024, 2025, and 2026, covering lots of research papers that apply SSMs to areas like medical imaging, human pose estimation, video understanding, 3D object detection, language modeling, image generation, and more. Each entry gives the paper's title, authors, and a link (usually to arXiv), sometimes with a link to code.

The repository also provides a contact email for suggestions and invites contributions or corrections from the community. It's an index/resource, not a software tool — its purpose is to help researchers track progress in SSM research and applications.

Note: The README does not explain what State Space Models are in technical detail; it only frames them as a research area and as an alternative to Transformers.