you can phisically find me (most of the times) at
School of Informatics, University of Edinburgh
3.18A Informatics Forum
10 Crichton Street Newington
Edinburgh EH8 9AB, UK

I can finally read!

01 Sep 2023

Thanks to Brexit, I am now a Reader (Associate Professor in US) in Machine Learning!

APRIL is online

26 Aug 2023

The website for my lab APRIL is online. Check our research out!

Looking for PhD students!

01 Jun 2023

['I have several fully-funded PhD positions for international students. ๐Ÿ‘‰See', 'here full post and how to apply๐Ÿ‘ˆ.']

ERC Starting Grant!

22 Nov 2022

Very happy and lucky to see that my ERC StG "UNREAL: A UNified REAsoning Layer for trustworthy ML" has been funded! I will be hiring soon.

2yr postdoc position on reasoning+learning!

12 Oct 2022

2 years postdoc position with me, Pasquale Minervini and Edoardo Ponti on "Gradient-based Learning of Complex Latent Structures". Consider applying!


05 Aug 2022

Amazing invited talks, papers and discussions at the 5th TPM Workshop I co-organized at UAI 2022! In general, UAI was incredible!

PC tutorial at Neurips2022!

20 Jul 2022

I will do a new tutorial on the current landscape of circuits with YooJung and Robert at NeurIPS 2022 in New Orleans.

Dagstuhl was a blast!

22 Apr 2022

The Dagstuhl Seminar on "Recent Advancements in Tractable Probabilistic Inference" I organized with Max, Kristian and Priyank ended very well!
The in-person TPM team at Dagstuhl

Workflow Chair AISTATS 2022

10 Sep 2021

I will be workflow chair at AISTATS 2022

New adventures in Caledonia!

09 Sep 2021

I am starting as a Lecturer (Assistant Professor) in Machine Learning at the Institute of Adaptive and Neural Computation at the School of Informatics in the University of Edinburgh. I am looking for PhD students, get in touch if you are interested!

I am on the job market!

01 Nov 2020

Get in touch with me if you know about open position in #AI, #ML and #probabilistic #inference requiring efficient and reliable models.
I did a few things in that space!

Dagsthul here we come!

10 Oct 2020

My proposal with Max Welling, Kristian Kersting and Priyank Jaini for a Dagsthul seminar on "New advances in tractable probabilistic inference" has been accepted!
Stay tuned!

PC Tutorial @ ECML-PKDD2020

14 Sep 2020

The latest incarnation of the Probabilistic Circuits tutorial was at ECML-PKDD 2020! We have a video!

Approximate WMI @ NeurIPS2020

10 Sep 2020

Our work on tracing the boundarines of tractability for probabilistic inference with algebraic constraints got accepted at NeurIPS2020!
See you there!


09 Sep 2020

RAEs will appear at COLING2020 as they can be effectively used to learn object-centric representations that are context- and category-aware and that greatly boost predictions in zero-shot learning in guessing games!

PC Tutorial @ ECAI2020

29 Aug 2020

Presenting a new version of the Probabilistic Circuits tutorial at ECAI 2020 was smooth! Slides here!


26 Aug 2020

Thanks to the UCL AI Centre for having me talking about RAEs. Slides here!

PCs @ PGM2020

01 Jul 2020

PGM2020 is going to be invaded by a battalion of papers on PCs! I am lucky to have partecipated at one on conditional SPNs with the Darmstadt squad and another one about learning structured-decomposable PC with the UCLA brigade!

EiNets + MP-WMI@ICML2020

01 Jun 2020

I won the lottery twice: both Einsum Networks (smodec PCs on streoids on GPUs) + MP-WMI (efficient message passing for the largest tractable class of WMI) got accepted at ICML 2020. Never been so lucky, I expect seriously bad events to happen soon to restore the balance in the force. Hence, recommending friends and relatives to be extremely careful.


07 Apr 2020

Quarentine and self-isolation are going good. I just have a bit of anxiety that it might end too soon.

visiting PL@MPI

07 Mar 2020

Visiting the MPI and PL group for just one week is definitely not enough. I also had the chance to present my personal view on enabling and supporting decision making via tractable probabilistic inference.
Slides of this invited talk are here.

pc tutorial@AAAI20

07 Feb 2020

We had the opportunity to present an extended version (4 hours) of the tutorial on probabilistic circuits at AAAI 2020. Slides are here.


18 Dec 2019

(After a rejection at ICCV) our skeptical inquiry of VAEs for generative modeling is accepted at ICLR 2020.
With Partha, Medhi, Michael and Bernhard we argue that regularized deterministic autoencoders work equally well!.

t prime@NeurIPS 2019

11 Dec 2019

Martin and I organized the first (of a long series, hopefully!) meeting of the tractable probabilistic inference community. Update: T-prime was a blast, thanks to everyone, and Relational AI and Uber in primis.
Intro slides here.

pc tutorial@Stanford

02 Dec 2019

A huge thanks to Stefano Ermon for allowing the tutorial on probabilistic circuits to be done during his course on deep generative models.
Slides here.


11 Oct 2019

The first result of this summer's work with Zhe, Fanqi, Paolo and Guy -- "Hybrid Probabilistic Inference with Logical Constraints: Tractability and Message Passing" -- accepted at the KR2ML workshop at NeurIPS2019.

Expected predictions@NeurIPS19

04 Sep 2019

We are going to present in Vancouver our take on reasoning about predictive models via tractable computation of expected predictions -- joint work with Pasha, YooJung, Yitao and Guy.


22 Jul 2019

What a chance to give an invited tutorial on tractable probabilistic modeling and (probabilistic circuits!) at UAI 2019 with Guy and Nico. Slides are here.

organizing TPM 2019

14 Jun 2019

I will be organizing with Tahrima, Daniel, Alejandro and Pedro the 3rd Workshop on Tractable Probabilistic Modeling at ICML 2019 in Long Beach.
update: thanks to all who submitted and partecipated... TPM went (surprisingly) well!


13 May 2019

First steps towards fully integrating deep representations and tractable inference: RAT-SPNs, to be presented at UAI 2019. With Robert, Karl, Alejandro, Martin, Kristian and Zoubin.

new adventures at UCLA

01 Apr 2019

Started as a postdoc under the supervision of Guy Van den Broeck at the StarAI Lab.
Let's see the trouble I am gonna make.