---
title: "Mamba: Linear-Time Sequence Modeling with Selective State Spaces"
description: "Mamba asks how a recurrent model with a fixed-size state can decide what information deserves to survive. Read it to see how input-dependent state-space parameters create content-aware persistence and reset, and how a fused parallel scan makes the resulting time-varying recurrence practical on GPUs."
canonical_url: "https://fanout.sh/daily/2026-08-07-mamba-selective-state-spaces"
md_url: "https://fanout.sh/daily/2026-08-07-mamba-selective-state-spaces.md"
last_updated: "2026-08-07"
access: "public"
---

# Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Mamba asks how a recurrent model with a fixed-size state can decide what information deserves to survive. Read it to see how input-dependent state-space parameters create content-aware persistence and reset, and how a fused parallel scan makes the resulting time-varying recurrence practical on GPUs.

## Paper details

- Authors: Gu and Dao

- Venue: COLM 2024

- Track: AI Research

- Difficulty: Medium

- Reading time: 55 min

- Original paper: https://arxiv.org/abs/2312.00752v2

## What you will learn

- Why fixed linear state-space dynamics can be trained as a convolution but cannot change their update rule according to token content.

- How input-dependent Δ, B, and C let a bounded recurrent state persist useful history, admit selected inputs, and reset at boundaries.

- Why Mamba needs kernel fusion, parallel scan, SRAM-local state expansion, and recomputation after giving up the global-convolution shortcut.

## Continue exploring

[Explore recurrent state](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Arnn): Open Fanout's RNN node and connect Mamba's selective state to hidden-state recurrence, LSTM-style gates, sequence compression, and long-context modeling.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md