| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Tue, 09 Dec 2025 09:44:31 GMT
access-control-allow-origin: *
etag: W/"6937ef7f-4b4e"
expires: Mon, 29 Dec 2025 00:28:59 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: ECA4:3ABDEF:809BBA:9094FE:6951C8F3
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 00:18:59 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210092-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766967540.726643,VS0,VE203
vary: Accept-Encoding
x-fastly-request-id: 30a9f0bbea5099fe976b62bacfa6380c83ac4d3f
content-length: 6075
Emtiyaz Khan's Homepage
Emtiyaz Khan
I am a (tenured) team director at the RIKEN center for Advanced Intelligence Project (AIP) in Tokyo where I lead the Adaptive Bayesian Intelligence Team. I am also a visiting professor at Technical University Darmstadt (Germany), and soon will be joining as a full professor (W3) there (affiliated with Hessian.AI and the Center of Excellence on Reasonable AI). I have served as Program Chair of AISTATS 2025, ICLR 2024, and ACML 2022, and regularly serve as a Senior Area Chair, Area Chair, and reviewer in all major machine-learning venues (NeurIPS, ICML, ICLR, and AISTATS). I am an Action Editor for the JMLR and TMLR. I am currently serving as General Chair of AISTATS 2026. Previously, I was a postdoc and then a scientist at Ecole Polytechnique Fédérale de Lausanne (EPFL), where I also taught two large machine learning courses and received a teaching award. I first joined EPFL as a post-doc with Matthias Seeger in 2013, was a scientist at EPFL in Matthias Grossglausser's lab from 2014-2016. Before that, I finished my PhD at UBC in 2012 under the supervision of Kevin Murphy.emtiyaz [at] gmail.com [or] emtiyaz.khan [at] riken.jp Mastodon ORCID
-
Open Positions
- PhD positions at TU Darmstadt (Germany) on Reasonable AI (closing date: Nov 16, 2025).
- New Post-doc and PhD positions are also available for a new ABI group at TU Darmstadt (Germany), starting Sep. 2026.
News
- [3 Dec, 2025] Keynote at the the 1st EurIPS conference (officially endorsed European version of NeurIPS) [ Slides ]
- [22 Sep, 2025] Two papers accepted at NeurIPS2025 on VL and EoS (spotlight) and Compact Memory.
- [22 Sep, 2025] New paper on Information Geometry of VB
- [26 June, 2025] Talk on ABI team achievements at the 3rd Bayes-Duality Workshop [ Slides ]
- [20 June, 2025] Keynote at Bayes Comp 2025, Singapore [ Slides ]
- [18 June, 2025] New paper on Posterior Correction
- [6 May, 2025] I will serve as General Chair for AISTATS 2026.
Research
The main goal of my research is to design AI systems that can quickly adapt to their surroundings, just like humans and animals. Over the years, my research has consistently shown that Bayesian principles provide promising ways to address this problem. I have enjoyed this journey and have had my own (personal) breakthroughs along the way. I enjoy making progress towards my goal, one day at a time. I do this because I believe in slow and rigorous scientific process that aims to add value to existing knowledge. I care deeply about people and am committed to promoting well-being, inclusion, diversity, equity, privacy, and justice in society.
For details of my research activities, see the following pages,
- Adaptive Bayesian Intelligence team at RIKEN-AIP
- The Bayes-Duality Project (funded by CREST)
- Summary of research for the year [2024] [2023] [2022] [2021] [2019] [2018] [2017]
We are thankful for the following funding (rough approximation because of inflation),
- (2021-2026, USD 2.23 Million) JST-CREST and French-ANR's grant, The Bayes-Duality Project
- (2020-2023, USD 167,000) KAKENHI Grant-in-Aid for scientific Research (B), Life-Long Deep Learning using Bayesian Principles
- (2020-2023, USD 11,000) KAKENHI Grant-in-Aid for Chellenging Research (Exloratory), Linear algebra for continuous learning of large neural networks, PI: Rio Yokota, Total Budget: JPY 19,710,000
- (2019-2022, USD 237,000) External funding through companies for several Bayes related projects
Research Highlights
- Posterior Correction
- The IVON optimizer (for training GPT-2 from scratch)
- Memory Perturbation
- SAM as Bayes
- The Bayesian Learning Rule
- Knowledge-Adaptation Priors
- Continual Deep Learning by Functional Regularisation of Memorable Past
- NeurIPS 2019 Tutorial on "Deep learning with Bayesian principles" [Slides] [SlidesLive] [YouTube]
- Practical Deep Learning with Bayesian Principles
- Bayesian Deep Learning using Weight-Perturbation in Adam (code here)
- Conjugate-Computation Variational Inference (CVI).