Papers › DeMansia: Mamba Never Forgets Any Tokens

DeMansia: Mamba Never Forgets Any Tokens

4 Aug 2024arXiv:2408.01986archive 2025-07-28

Ricky Fang

This paper examines the mathematical foundations of transformer architectures, highlighting their limitations particularly in handling long sequences. We explore prerequisite models such as Mamba, Vision Mamba (ViM), and LV-ViT that pave the way for our proposed architecture, DeMansia. DeMansia integrates state space models with token labeling techniques to enhance performance in image classification tasks, efficiently addressing the computational challenges posed by traditional transformers. The architecture, benchmark, and comparisons with contemporary models demonstrate DeMansia's effectiveness. The implementation of this paper is available on GitHub at https://github.com/catalpaaa/DeMansia

PaperPDFCode

Code

catalpaaa/demansia officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationMambaState Space Modelsimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LV-ViTMamba

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections