Mateusz Gajewski
mateuszgajewski.bsky.social
Mateusz Gajewski
@mateuszgajewski.bsky.social
ML PhD Student
Interested in causality
Reposted by Mateusz Gajewski
From time to time I write about the need to do interdisciplinary research when AI is used to solve problems from other disciplines. Yesterday, our paper on “Implicit modeling of equivariant tensor basis with Euclidean turbulence closure neural network” was published pubs.aip.org/aip/pof/arti...
February 8, 2025 at 8:44 AM
Reposted by Mateusz Gajewski
🚨 Image AutoRegressive Models Leak More Training Data Than Diffusion Models🚨

IARs — like the #NeurIPS2024 Best Paper — now lead in AI image generation. But at what risk?

IARs:
🔍 Are more likely than DMs to reveal training data
🖼️ Leak entire training images verbatim

🧵 1/
February 5, 2025 at 6:36 PM
Reposted by Mateusz Gajewski
Love question 2 from @tenanatc.bsky.social

Ciaran Lee from Spotify worked on quantum causal models and it seems we have a pretty good ways to go from the quantum to deterministic structural models.

We discuss it briefly in the upcoming episode of the Causal Bandits Podcast.

#CausalSky
Alright #Statsky, let's unpack this.

Causal Discovery requires:

1. Faithfullness Assumption: all interdependencies
observed in the data are structural, resulting from the structure of the causal graph, and not accidental.

2. Determinism: Is Causality deterministic? Is life deterministic?
....
This is my issue with "Causal Discovery" and "Causal AI"... if you actually *think* about what's being done, it isn't clear that there is anything causal going on at all most of the times, it's just a different version of a correlation matrix.
January 24, 2025 at 6:29 PM
Reposted by Mateusz Gajewski
To były dwa bardzo intensywne dni w Davos.
- W czwartek rano panel w Poland Biznes Hub o dekarbonizacji
- W czwartek w południe, to panel w Belgium House, gdzie mowę wstępną wygłosił premier Belgii
- W piątek rano "polski" panel w AI House, o znaczeniu lokalnych talentóe dla globalnych innowacji
January 24, 2025 at 4:42 PM
Reposted by Mateusz Gajewski
500 miliardów dolarów - tyle Stany Zjednoczone planują wydać na centra obliczeniowe dla AI w najbliższych 4 latach. Wczoraj ten plan ogłosił Donald Trump razem z Masayoshi Sonem - CEO SoftBank, Samem Altmanem - CEO OpenAI oraz Larrym Ellisonem - prezesem Oracle -
www.theverge.com/2025/1/21/24....
OpenAI and Softbank are starting a $500 billion AI data center company
Nvidia, Microsoft, and Arm are among the technology partners.
www.theverge.com
January 22, 2025 at 8:10 AM
Reposted by Mateusz Gajewski
Polecam moją rozmowę z
Beatą Mońką w Interii biznes.interia.pl/gospodarka/n... między innymi o tym gdzie jesteśmy aktualnie w Polsce w rozwoju AI.
USA ograniczą dostęp do chipów. Co to oznacza dla Polski?
W Stanach Zjednoczonych przepływ ludzi pomiędzy nauką i biznesem jest płynny. Naukowcy tworzą firmy, zakładają start-upy. Prof. Piotr Sankowski zwraca uwagę,
biznes.interia.pl
January 17, 2025 at 7:39 AM
Reposted by Mateusz Gajewski
That was @neuripsconf.bsky.social 2024 seen through the eyes of IDEAS NCBR researchers
See more ➡️ ideas-ncbr.pl/en/ideas-ncb... #neurips
December 19, 2024 at 2:41 PM
Reposted by Mateusz Gajewski
I am totally in the FOMO mode, seeing #NeurIPS24 messages. I’m not there :( this year.

However, I recommend chatting with my co-authors and students :) @bartoszpiotrowski.bsky.social @albertqjiang.bsky.social @michalnauman @mateuszostaszewski.bsky.social

2 papers on the main track and spotlight
December 12, 2024 at 2:37 PM
Reposted by Mateusz Gajewski
Duże konferencje są dobre bo są dobre i duże ;). NeurIPS 2024 to 16500 uczestników, co pokazuje dlaczego warto tutaj publikować, bo każda opublikowana praca z definicji dostaje kilkunastotysięczne audytorium. O naszej widoczności na NeurIPS pisał też Kuba Pachocki (główny naukowiec w OpenAI).
December 11, 2024 at 3:24 PM
Reposted by Mateusz Gajewski
Cool news. Our paper "Accurate estimation of feature importance faithfulness for tree models" (arxiv.org/pdf/2404.03426) with Mateusz Gajewski, Adam Karczmarz, Mateusz Rapicki has just been accepted to AAAI conference (aaai.org/conference/a...).
AAAI-25 - AAAI
aaai.org
December 10, 2024 at 10:13 AM
How would you evaluate a new causal discovery method? A new paper by Brouillard et al. challenges the common approaches and suggests a rethink. Here’s what they found 🧵👇
arxiv.org/abs/2412.01953

#CausalSky
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many scientific disciplines. However, its real-world applications remain l...
arxiv.org
December 5, 2024 at 3:26 PM
Reposted by Mateusz Gajewski
I have created a starter pack for the Polish ML community. Let's grow it together! Let me know if you know somebody who should be included.
go.bsky.app/TSkgFjK
November 21, 2024 at 8:13 AM