Postdoc researcher at @DTUtweet. PhD at @uc3m. Former visiting researcher at @Cambridge_Uni. Probabilistic ML, DL
Copenhague, Dinamarca
Joined September 2019
- Tweets53
- Following305
- Followers94
- Likes368
Incredibly honored to share that I have been selected by #laCaixaFoundation as Postdoctoral Junior Leader Fellow (Incoming). Over the next years, I will lead a research line on flow-based generative modelling and meta-learning at @IMAG_UGR, @CanalUGR .
1/ 🚀 Congratulations to the new researchers selected in the #laCaixaFoundation Postdoctoral Junior Leader #Fellowships of the 2025 Call! 👏
These 40 researchers are ready to shape the future of STEM. 🤩
Ignacio Peis retweeted
NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS.
Read more in our blog post and on the EurIPS website:
blog.neurips.cc/2025/07/16/n…
eurips.cc/
Ignacio Peis retweeted
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅
EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @NeurIPSConf and #NordicAIR and is co-developed by @ELLISforEurope
eurips.cc
Ignacio Peis retweeted
Excited to prepare for #GenU2024! 🎉 Thrilled to welcome an incredible lineup of speakers again this year!
genu.ai/2024/
@WouterBoomsmaDK @pamattei @OleWinther1
Ignacio Peis retweeted
📢 The 1st episode of our web series, AI Connects, is out now! Check it out here 👉 aicentre.dk/ai-connects/epis…
This quoted post is unavailable.
📢 Exciting opportunity to work with an outstanding team of researchers! 📢
Feel free to reach out to us if you want to know more details about the ongoing projects!
We seek a postdoc (2-yr) at DTU specialising in generative modelling. Focus on diffusion & score-based models applied to physical systems.
Interested? Contact me or learn more: groups.google.com/g/ml-news/…
Check out our ongoing work: arxiv.org/abs/2405.05981
Please RT! #Postdoc
Ignacio Peis retweeted
Application deadline is approaching (April 30th): We are looking for two postdocs in Generative Modelling at DTU Compute: one within physical systems (w/ @rasbjo) and one within life science (w/ mlls.dk).
efzu.fa.em2.oraclecloud.com/…
Please RT.
Ignacio Peis retweeted
We're looking for two postdocs in Generative Modelling at DTU: one within physical systems (w/@rasbjo, @berianjames, @IgnacioPeis) and one within life science (w/ mlls.dk).
Both are methodological and prioritising advancement of DGMs.
efzu.fa.em2.oraclecloud.com/…
Ignacio Peis retweeted
➡️El próximo 20 de diciembre tendrá lugar en la UPO el I encuentro @Andaluz_IA sobre #investigación en #InteligenciaArtificial en #Andalucía.
🤖Con la presentación de más de 50 investigaciones en diversos ámbitos de la #IA: procesamiento del lenguaje natural, aprendizaje automático y profundo, #bigdata, razonamiento automático, visión por computador, #robótica, etc
sites.google.com/view/andalu…
🏄🏼♂️🌴 I’m counting the hours to meet old and new friends at Honolulu! 🌴🏄🏼♂️
We’ll be presenting this precious piece of work at this year @icmlconf :
arxiv.org/pdf/2302.06223.pdf
Visit us for details at Exhibit Hall 1 #432 on Thursday 27 Jul at 10:30 am (Poster Session 5)! ⏱️
I am thrilled to announce that I will join @jesfrellsen 's group at @DTU_Compute as postdoc!
I got one of the six fellowships from the @DataScienceDK . Thanks everyone for your support!
See you all soon in Copenhagen!🇩🇰
Last Friday, I gave a talk at the @AiCentreDK on improved MCMC-based inference for actively acquiring missing information.
It was a truly rewarding experience to meet such a group of passionate and engaged researchers!
[Slides]: ipeis.github.io/assets/pdf/0…
Ignacio Peis retweeted
Our work, VaMoH, has been accepted at #ICML2023 ! Can't wait to present our work and looking forward to meeting you all in Hawaii! @ML_pablosm @IgnacioPeis @IValeraM
🚨 #VAMoH is available! 🚨
Exciting news! 🥳 Our latest paper “Variational Mixture of HyperGenerators for learning distributions over functions” is now on ArXiv.
Link: arxiv.org/abs/2302.06223
@ML_pablosm @IgnacioPeis Pablo M. Olmos @IValeraM
#GenerativeModeling
🧵(1/n)
Ignacio Peis retweeted
We have just updated our manuscript. Now, you can find out how efficient VaMoH is in inference times. It is at least 2 times faster when compared to baselines! 🚀
Really excited to share this preprint, where we leverage the strengths of VAEs and Flows for learning Implicit Neural Representations (INRs). Amazing team! 👏
🚨 #VAMoH is available! 🚨
Exciting news! 🥳 Our latest paper “Variational Mixture of HyperGenerators for learning distributions over functions” is now on ArXiv.
Link: arxiv.org/abs/2302.06223
@ML_pablosm @IgnacioPeis Pablo M. Olmos @IValeraM
#GenerativeModeling
🧵(1/n)
Ignacio Peis retweeted
🚨 #VAMoH is available! 🚨
Exciting news! 🥳 Our latest paper “Variational Mixture of HyperGenerators for learning distributions over functions” is now on ArXiv.
Link: arxiv.org/abs/2302.06223
@ML_pablosm @IgnacioPeis Pablo M. Olmos @IValeraM
#GenerativeModeling
🧵(1/n)
Ignacio Peis retweeted
We're at @NeurIPSConf in New Orleans with 14 papers! Come and have a chat with us and our fantastic collaborators :D See our #NeurIPS2022 schedule below!
If you ever struggled with properly defining the hyperparameters of your MCMC method, or having a good initial state, this PyTorch code I recently released for automatically tuning them in HMC, might be of your interest:
github.com/ipeis/HMCTuning
Don’t waste a million samples! Momentum variances, step sizes and scaling factors for the proposal can be optimised via Variational Inference. Check how the exploration improves during the optimization:
You can try your target! Even the intractable posterior distribution of your deep generative model, as we did in arxiv.org/abs/2202.04599 .
