Gergely Neu
full-time ML theory nerd, part-time AI-non enthusiast
- Reposted by Gergely NeuALT TXT - dashare.zone ADMIN
- our team at @upf.edu is hiring a POSTDOC on graphical models and statistical learning! deadline: jan 30
- more info: shorturl.at/1DVxE
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely NeuWildly different things, tasks, techniques, subspecialties being lumped into "AI" and then being conflated with each other, doesn't help. Different types of models vs the techniques to train them vs the tasks they are supposed to accomplish, all under "AI".
- when in stockholm
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- one of those (innumerable) days when i just can't get @6organs.bsky.social tunes out of my head. guess I'll just have to lean into it
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- immensely grateful & happy to be among the recipients 🙏🙏🙏
- The results of the ERC Consolidator Grant call have been announced! 📣 349 researchers have been selected for funding. Congratulations to all! #ERCCogG! 👉 buff.ly/uu62uFV #FrontierResearch #EUfunded #HorizonEurope @scienceinnovation.ec.europa.eu
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- happy to finally share some BIG news: today i'm starting a new job as an ICREA research professor (@icreacommunity.bsky.social) at @upf.edu. this is literally the best job ever and i'm looking forward to all the exciting work i'll get to do now that i am tenured!
- looking at you #AISTATS2025
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- i'm looking forward to attending & contributing to the first ever EurIPS meeting (@euripsconf.bsky.social #EurIPS)! glad that i can learn about the most exciting ML research without having to travel to the US to attend a 15k+ person conference. some personal highlights of the program below. 1/n
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- check out this PhD opportunity for female students from Africa at @upf.edu : www.upf.edu/web/phd-engi... i have hired my amazing student @NnekaOkolo4 via this program, which was a great success. hope i can find someone this time as well! let me know if you have any questions
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely NeuI’m excited to announce that my new book, _The Irrational Decision_, is now available for pre-order from Princeton University Press.
- Reposted by Gergely NeuNEVER !! - dashare.zone ADMIN
- dear reviewers, of course that "no pdf" rebuttal policy is not going to stop me from running all those wonderful new baselines you just suggested, please find the results below
- Reposted by Gergely Neu[Not loaded yet]
- what's the opposite of FOMO called again? either way, i'm right in the middle of that (hope everyone else is doing fine at #ICML2025 nevertheless!)
- great initiative -- I'll be there!
- Reposted by Gergely Neu[Not loaded yet]
- Reposted by Gergely Neu[Not loaded yet]
- wanna know how to do inverse Q-learning right? read this paper then!! joint work with the best team of students ever ♥️
- new preprint with the amazing @lviano.bsky.social and @neu-rips.bsky.social on offline imitation learning! learned a lot :) when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!
- new work on computing distances between stochastic processes ***based on sample paths only***! we can now: - learn distances between Markov chains - extract "encoder-decoder" pairs for representation learning - with sample- and computational-complexity guarantees read on for some quick details.. 1/n
- in a 2024 paper (w/ Sergio Calo, Anders Jonsson, Ludovic Schwartz & Javier Segovia-Aguas), we explored the question of defining and computing similarity metrics between Markov chains (arxiv.org/abs/2406.04056). we are back asking the same question, and giving some even more satisfying answers 2/n
