Sign in

Christian A. Naesseth

@canaesseth.bsky.social
2.9K followers 552 following 115 posts

Assistant Professor of Machine Learning Generative AI, Uncertainty Quantification, AI4Science Amsterdam Machine Learning Lab, University of Amsterdam naesseth.github.io

PostsRepliesMedia
Reposted by Christian A. Naesseth
Erik Bekkers @erikjbekkers.bsky.social · 15/04/2026
We're looking for a new colleague at @amlab.bsky.social: Assistant Professor in AI for Science 🔬🤖 World-class ML research, Amsterdam's thriving AI ecosystem (ELLIS, startups, big tech), and some of the best academic labor conditions in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancies...
werkenbij.uva.nl
Vacancy — Assistant Professor in AI for Science (AI4Science)
<p><span>Are you passionate about advancing Machine Learning by integrating insights from the natural sciences? Are you eager to bridge the 3rd (<em><span>computational</span></em>) and 4th (<em><span...
03316
Reposted by Christian A. Naesseth
Symposium on Probabilistic Machine Learning @probml.bsky.social · 10/02/2026
ProbML 2026 (formerly AABI) invites submissions on probabilistic ML (both Bayesian and otherwise!), July 5 in Seoul (co-located with ICML). Website: probml.cc. Tracks: proceedings (PMLR), workshop, fast track. New focus includes applications in healthcare and climate! Submit by: 20 March 2026.
12516
Christian A. Naesseth @canaesseth.bsky.social · 16/07/2025
At #ICML2025 this week? Come check out our work on controlled generation, simulation-free latent SDEs, and risk monitoring in test-time adaptation, and chat with the awesome students that made it happen! #SDE #Diffusion #FlowMatching #TTA #UncertaintyQuantification
151
Christian A. Naesseth @canaesseth.bsky.social · 30/06/2025
🚨🚀 Come hear @gbarto.bsky.social talk about SDE Matching tomorrow! SDE Matching is a highly efficient and scalable training framework for Latent/Neural SDEs. You no longer have to discretize or simulate your SDE models when fitting them to data. #SDE #Diffusion #FlowMatching #ML
191
Christian A. Naesseth @canaesseth.bsky.social · 14/05/2025
Overleaf down 😅 #Overleaf #NeurIPS
media.tenor.com
a cartoon dog is sitting at a table with a cup of coffee in front of a fire with the words this is fine .
ALT: a cartoon dog is sitting at a table with a cup of coffee in front of a fire with the words this is fine .
0130
Christian A. Naesseth @canaesseth.bsky.social · 07/05/2025
Wow, I am floored! With the UAI results in, my lab with collaborators have achieved the #PerfectGame 🏆 100% acceptance rate across an entire #ML cycle! (5/5 #NeurIPS, #ICLR, 2/2 #AISTATS, 2/2 #ICML, 1/1 #UAI) 10 for 10. 🥳🍾🤩 #Science #AI #ElementalAI
1100
Reposted by Christian A. Naesseth
AMLab @amlab.bsky.social · 06/05/2025
Exciting news: AMLab is happy to have 7 papers accepted at #ICML2025! 🎉 See the thread below for the full list 📝 and meet us in Vancouver to discuss them further! 🇨🇦 🧵1 / 8
1144
Christian A. Naesseth @canaesseth.bsky.social · 03/05/2025
#AISTATS2025 happening in Phuket, Thailand! I have two papers at the conference: 1. Max-Rank: Efficient Multiple Testing for Conformal Prediction 2. Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space Both at poster session 2!
1121
Christian A. Naesseth @canaesseth.bsky.social · 30/04/2025
Very excited that our work (together with my PhD student @gbarto.bsky.social and our collaborator Dmitry Vetrov) was recognized with a Best Paper Award at #AABI2025! #ML #SDE #Diffusion #GenAI 🤖🧠
1182
Christian A. Naesseth @canaesseth.bsky.social · 29/04/2025
If you missed it and are attending #AABI at NTU today you can find me presenting it again at the afternoon poster session! approximateinference.org
approximateinference.org
Home
072
Christian A. Naesseth @canaesseth.bsky.social · 28/04/2025
Come check out SDE Matching at the #ICLR2025 workshops, a new simulation-free framework for training fully general Latent/Neural SDEs (generalisation of diffusion and bridge models). FPI: Morning poster session DeLTa: Afternoon poster session #SDE #Bayes #GenAI #Diffusion #Flow
1131
Reposted by Christian A. Naesseth
ICLR Conference @iclr-conf.bsky.social · 23/04/2025
The calm before the storm #ICLR2025 🔥🔥🔥
0486
Christian A. Naesseth @canaesseth.bsky.social · 21/04/2025
Attending #ICLR2025 and #AABI2025. Presenting at the conference and workshops: 1. E-Valuating Classifier Two-Sample Tests, Friday, Hall 3 + Hall 2B #437 2. SDE Matching, Sunday-Tuesday, FPI/DeLTa/AABI openreview.net/forum?id=dwF... arxiv.org/abs/2502.02472 lmk if you want to chat!
openreview.net
E-Valuating Classifier Two-Sample Tests
We introduce a powerful deep classifier two-sample test for high-dimensional data based on E-values, called E-C2ST. Our test combines ideas from existing work on split likelihood ratio tests and...
1140
Reposted by Christian A. Naesseth
Sander Dieleman @sedielem.bsky.social · 15/04/2025
New blog post: let's talk about latents! sander.ai/2025/04/15/l...
sander.ai
Generative modelling in latent space
Latent representations for generative models.
37518
Reposted by Christian A. Naesseth
David Rügamer @davidruegamer.bsky.social · 12/04/2025
Working on probabilistic modeling, inference, and decision-making? Join us at #AABI 2025 if you’re going to Singapore later this month! Register here (free but spots are limited!): approximateinference.org
approximateinference.org
Home
172
Christian A. Naesseth @canaesseth.bsky.social · 13/04/2025
Make sure to get your tickets to AABI if you are in Singapore on April 29 (just after #ICLR2025) and interested in probabilistic modeling, inference, and decision-making! Tickets (free but limited!): lu.ma/5syzr79m More info: approximateinference.org #Bayes #MachineLearning #ICLR2025 #AABI2025
0178
Reposted by Christian A. Naesseth
Serge Belongie @serge.belongie.com · 30/03/2025
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
docs.google.com
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
6279161
Christian A. Naesseth @canaesseth.bsky.social · 15/03/2025
Don't forget to submit your Fast-Track papers to #AABI2025 today! If you have an accepted paper in machine learning since AABI 2024 present it as a poster. CfP: approximateinference.org/call/ Looking forward to seeing everyone in Singapore on April 29, just after #ICLR2025!
approximateinference.org
Call for Papers
044
Christian A. Naesseth @canaesseth.bsky.social · 10/03/2025
A bit unfortunate that AC_CONF_LIST doesn't include AISTATS or UAI...
060
Reposted by Christian A. Naesseth
Pierre Alquier @pierrealquier.bsky.social · 05/03/2025
I already advertised for this document when I posted it on arXiv, and later when it was published. This week, with the agreement of the publisher, I uploaded the published version on arXiv. Less typos, more references and additional sections including PAC-Bayes Bernstein. arxiv.org/abs/2110.11216
110821
Christian A. Naesseth @canaesseth.bsky.social · 12/02/2025
This is really interesting! Learning the posterior probability path p(x0 | xt) rather than only the mean is something we suggested in Variational Flow Matching as well, but for a different reason (generating discrete data). Very cool that it can also be used for faster generation.
0130
Christian A. Naesseth @canaesseth.bsky.social · 12/02/2025
You still have a chance to submit your work to all tracks for AABI. New deadline is February 14 for both Workshop and Proceedings track! #AABI2025 #ML #ICLR2025 #Stats #Bayes
053
Christian A. Naesseth @canaesseth.bsky.social · 07/02/2025
media.tenor.com
a man is sweating profusely and looking at the camera .
ALT: a man is sweating profusely and looking at the camera .
020
Christian A. Naesseth @canaesseth.bsky.social · 06/02/2025
We have extended the #AABI workshop and proceedings deadlines! *New deadlines:* Workshop Track: February 14, AoE Proceedings Track: February 14, AoE approximateinference.org/call/ #ProbML #AABI #ICLR #Bayes
approximateinference.org
Call for Papers
083
Christian A. Naesseth @canaesseth.bsky.social · 05/02/2025
Really excited about this! We note a connection between diffusion/flow models and neural/latent SDEs. We show how to use this for simulation-free learning of fully flexible SDEs. We refer to this as SDE Matching and show speed improvements of several orders of magnitude. arxiv.org/abs/2502.02472
arxiv.org
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend ...
05010
Reposted by Christian A. Naesseth
Tim G. J. Rudner @timrudner.bsky.social · 05/02/2025
Submit your work to the 7th Symposium on Advances in Approximate Bayesian Inference! #AABI This year, #AABI will be co-located with #ICLR2025! Workshop Track: February 7, AoE Proceedings Track: February 7, AoE Fast Track: February 18 / March 14, AoE approximateinference.org/call/
approximateinference.org
Call for Papers
1196
Christian A. Naesseth @canaesseth.bsky.social · 04/02/2025
Don't forget #AABI, the Symposium on Advances in Approximate Bayesian Inference is coming to Singapore!! Co-located #ICLR2025 Workshop Track: February 7, AoE Proceedings Track: February 7, AoE Fast Track: February 18 / March 14, AoE approximateinference.org/call/ #ML #Bayes #GenAI
approximateinference.org
Call for Papers
0186
Reposted by Christian A. Naesseth
Sander Dieleman @sedielem.bsky.social · 22/01/2025
📢PSA: #NeurIPS2024 recordings are now publicly available! The workshops always have tons of interesting things on at once, so the FOMO is real😵‍💫 Luckily it's all recorded, so I've been catching up on what I missed. Thread below with some personal highlights🧵
112833
Christian A. Naesseth @canaesseth.bsky.social · 22/01/2025
Interesting 🤔 Reminds me of our work on combining multi-proposals with "multi-chains". This worked best by splitting compute at 50/50 between the number of (interacting) Markov chains and independent proposals. proceedings.mlr.press/v48/rainfort...
proceedings.mlr.press
Interacting Particle Markov Chain Monte Carlo
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers. Like related methods, i...
040
Christian A. Naesseth @canaesseth.bsky.social · 22/01/2025
#AISTATS decisions are out! My lab went 2 for 2 😀 I would also recommend having a look at submitting to the AABI fast-track or workshop track that happens in-between ICLR and AISTATS in Singapore: approximateinference.org
2250
Reposted by Christian A. Naesseth
David Rügamer @davidruegamer.bsky.social · 21/01/2025
Eagerly waiting for #ICLR2025 or #AISTATS2025 results? Are you working on probabilistic #ML, #GenAI, approximate methods, or #UQ? Then check out #AABI held on Apr 29 co-located with #ICLR2025 + Fast-Track for accepted ICLR/AISTATS submissions -> approximateinference.org
approximateinference.org
Home
3123
Reposted by Christian A. Naesseth
ELLIS @ellis.eu · 18/12/2024
The ELLIS Pre-NeurIPS Fest 2024 was a big success! 🎉 Thousands attended & hundreds of posters were showcased across 17 ELLIS Sites. A great platform for ELLIS researchers to connect with #AI & #ML enthusiasts. Thanks to all participating Sites! 👏 #ELLISforEurope #NeurIPS2024
A researcher points to a poster at the ELLIS Unit Warsaw eventScientists and researchers gather at an ELLIS Unit Amsterdam event to look at NeurIPS postersScientists and researchers look at NeurIPS posters at an ELLIS Unit Copenhagen eventTwo scientists look at a NeurIPS poster at an ELLIS Institute Tübingen event
0272
Reposted by Christian A. Naesseth
Alex Thiery @alexxthiery.bsky.social · 15/12/2024
One #postdoc position is still available at the National University of Singapore (NUS) to work on sampling, high-dimensional data-assimilation, and diffusion/flow models. Applications are open until the end of January. Details: alexxthiery.github.io/jobs/2024_di...
04118
Reposted by Christian A. Naesseth
Arnaud Doucet @arnauddoucet.bsky.social · 15/12/2024
The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here drive.google.com/file/d/1eLa3...
drive.google.com
BreimanLectureNeurIPS2024_Doucet.pdf
932868
Christian A. Naesseth @canaesseth.bsky.social · 13/12/2024
Today is Lucia, not really celebrated much outside Sweden. But it's a fun tradition with lots of candles, song, snacks, glögg, etc. For now here is a pic with Christmas tree 🎄 at work #Lab42 #NeuralNetworks #ML
390
Reposted by Christian A. Naesseth
Jan-Willem van de Meent @jwvdm.bsky.social · 12/12/2024
Come talk to @zmheiko.bsky.social about his work on sample-efficient black box variational inference! (East Exhibition Hall #4105)
0172
Reposted by Christian A. Naesseth
Jan-Willem van de Meent @jwvdm.bsky.social · 12/12/2024
François Cornet and @gbarto are presenting their work on Equivariant Neural Diffusion now at East Exhibition #2403!
0142
Reposted by Christian A. Naesseth
Jan-Willem van de Meent @jwvdm.bsky.social · 12/12/2024
Here are the dapper @metodjazbec.bsky.social and Alexander Timans, presenting their work on early-exit with risk control.
1172
Christian A. Naesseth @canaesseth.bsky.social · 13/12/2024
Check out this work from my group that @gbarto.bsky.social will present later today! Diffusion (bridges)/flows with learnable probability paths (simulation-free!) that can make your generative model better (SOTA CIFAR-10 and ImageNet) and faster!
1191
Christian A. Naesseth @canaesseth.bsky.social · 12/12/2024
Today my collaborators are presenting no less than 3 of our papers at #NeurIPS2024 Come check out the posters and talk to everyone to find out more about molecule generation, early-exit with risk control, or speeding up variational inference!
1121
Reposted by Christian A. Naesseth
Andrew Gordon Wilson @andrewgwils.bsky.social · 11/12/2024
Every year at NeurIPS, I get a sense of where the community is headed. I'm so happy that the era of larger language models on larger datasets is coming to an end.
41116
Reposted by Christian A. Naesseth
Sander Dieleman @sedielem.bsky.social · 12/12/2024
When a bunch of diffusers sit down and talk shop, their flow cannot be matched😎 It's time for the #NeurIPS2024 diffusion circle! 🕒Join us at 3PM on Friday December 13. We'll meet near this thing, and venture out from there and find a good spot to sit. Tell your friends!
It's located near the west entrance to the west side of the conference center, on the first floor, in case that helps!
1427
Christian A. Naesseth @canaesseth.bsky.social · 11/12/2024
This is happening today! Unfortunately I couldn't be there, but go talk to @eijkelboomfloor.bsky.social @gbarto.bsky.social @jwvdm.bsky.social about our work on Variational Flow Matching.
0173
Reposted by Christian A. Naesseth
AMLab @amlab.bsky.social · 09/12/2024
🪪VISA: Variational Inference with Sequential Sample-Average Approximations by @zmheiko.bsky.social, @canaesseth.bsky.social, @jwvdm.bsky.social 🪪https://neurips.cc/virtual/2024/poster/93819 📜https://arxiv.org/abs/2403.09429 🧵8 / 12
163
Reposted by Christian A. Naesseth
AMLab @amlab.bsky.social · 09/12/2024
🚪Fast yet Safe: Early-Exiting with Risk Control by @metodjazbec.bsky.social*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, @canaesseth.bsky.social, Eric Nalisnick 🪪https://neurips.cc/virtual/2024/poster/94477 📜https://arxiv.org/abs/2405.20915 🧵6 / 12
162
Reposted by Christian A. Naesseth
AMLab @amlab.bsky.social · 09/12/2024
🦠Equivariant Neural Diffusion for Molecule Generation by François Cornet, @gbarto.bsky.social, Mikkel Schmidt, @canaesseth.bsky.social 🪪https://neurips.cc/virtual/2024/poster/96702 🧵4 / 12
161
Reposted by Christian A. Naesseth
AMLab @amlab.bsky.social · 09/12/2024
⚙️Variational Flow Matching for Graph Generation by @eijkelboomfloor.bsky.social *, @gbarto.bsky.social*, @canaesseth.bsky.social, @wellingmax.bsky.social, @jwvdm.bsky.social 🪪https://neurips.cc/virtual/2024/poster/94958 📜https://arxiv.org/abs/2406.04843 🧵3 / 12
2143
Reposted by Christian A. Naesseth
AMLab @amlab.bsky.social · 09/12/2024
🌊Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling by @gbarto.bsky.social , Dmitry Vetrov, @canaesseth.bsky.social 🪪https://neurips.cc/virtual/2024/poster/94656 📜https://arxiv.org/abs/2404.12940 🧵2 / 12
141
Christian A. Naesseth @canaesseth.bsky.social · 09/12/2024
#NeurIPS2024 #ML
2754
Christian A. Naesseth @canaesseth.bsky.social · 08/12/2024
Some good reading tips, especially if you're interested in the fundamentals of Monte Carlo methods! #SMC #IS #Sampling #RNG
090