Albert Gu
Co-author of Mamba and first author of S4; CMU assistant professor and Cartesia co-founder
- Assistant Professor, Machine Learning Department; leads the Goomba Lab, Carnegie Mellon University12
- Chief Scientist & Co-founder, Cartesia3
Albert Gu is an Assistant Professor in the Machine Learning Department at Carnegie Mellon University, where Albert Gu leads the Goomba Lab research group, and the Chief Scientist and a co-founder of Cartesia. Albert Gu is first author of the S4 paper on structured state space models and, with Tri Dao, co-first author of the Mamba and Mamba-2 papers. The Apache-2.0 Mamba repository, whose AUTHORS file lists Albert Gu, provides the official implementation.12345678
Research
Albert Gu's research centres on state space models for long sequences. With Tri Dao, Christopher Ré and others, Gu was first author of HiPPO (2020), a framework for recurrent memory based on optimal polynomial projections, and of the 2021 paper on linear state-space layers that unify recurrent, convolutional and continuous-time models.910
Gu's S4 paper (2021) made structured state space models efficient for long-range sequence tasks. Gu and Tri Dao were then co-first authors of Mamba (2023), which adds input-dependent selection to state space models, and of Mamba-2 (2024), which connects state space models and attention through structured state space duality.4567
Gu is the last-listed author of the 2025 paper on dynamic chunking for end-to-end hierarchical sequence modeling, the basis of the H-Net architecture, and of the March 2026 Mamba-3 paper, whose author list also includes Tri Dao.111213
Teaching and lab
Cartesia
Work
Mamba and Mamba-2 (external site: github.com)Open-source code
Co-first author with Tri Dao of the Mamba (2023) and Mamba-2 (2024) papers, and listed in the AUTHORS file of the Apache-2.0 repository that provides the official implementation.5678
S4 (structured state space models) (external site: arxiv.org)Published research
First author, with Karan Goel and Christopher Ré, of the paper Efficiently Modeling Long Sequences with Structured State Spaces.4
Career timeline
Aug 2020
Released HiPPO, a framework for recurrent memory with optimal polynomial projections, as first author.9
Oct 26, 2021
Released the linear state-space layers paper as first author.10
Oct 31, 2021
Released the S4 paper on structured state space models as first author.4
Dec 2023
May 2024
Released Mamba-2 and the structured state space duality framework with Tri Dao.6
Jul 2025
Co-authored the dynamic chunking paper behind the H-Net hierarchical architecture.11
Mar 16, 2026
Co-authored the Mamba-3 paper on improved sequence modeling with state space principles.12
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Arjun DesaiAlso at Cartesia
- Beren MillidgeLanguage models
- Abigail SeeAlso from Stanford
- Brandon YangAlso at Cartesia
- Fabian PedregosaMachine-learning theory
- Abubakar AbidAlso from Stanford
- Graham NeubigAlso at Carnegie Mellon University
- Michael CollinsLanguage models
- Alex SmolaAlso at Carnegie Mellon University
- Jun-Yan ZhuAlso at Carnegie Mellon University
- Sébastien BubeckLanguage models
- Alexei A. EfrosAlso at Carnegie Mellon University
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/albert-gu/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/albert-gu/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Albert Gu — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.