---
license: mit
language:
- en
---
# Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

The official checkpoint release of ICLR 2025 paper "[Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing](https://arxiv.org/abs/2501.00658)".

Peihao Wang, Ruisi Cai, Yuehao Wang, Jiajun Zhu, Pragya Srivastava, Atlas Wang, Pan Li

Please refer to our [GitHub repo](https://github.com/VITA-Group/SSM-Bottleneck) for more information.