
Assistant Professor, ELLIS Scholar | @AmlabUva @UvA_Amsterdam @Ellis_Amsterdam | Generative AI, Uncertainty Quantification, AI4X
Joined February 2014
- Tweets1.7K
- Following482
- Followers2.3K
- Likes3K
Christian A. Naesseth retweeted
🎉 The new ELLIS Unit in Sweden was inaugurated! It aims to boost AI research and collaboration in Sweden and across Europe, with research activities focusing on the foundations of AI, AI for scientific discovery, and AI for technology and society. bit.ly/3WjKqVJ
Christian A. Naesseth retweeted
It’s weird how people treat the Nobel prize, or any award, as the pinnacle of a scientists career, or an ultimate aspiration. Doing work that you believe to have value should count for so much more than political winds, networking, and peer approval.
Christian A. Naesseth retweeted
What is TMLR doing under a 300% increase in submissions?
- Suspensions of >150 authors
- Publicly naming major violations
- Submission quotas distinguishing slop patterns
- Desk rejections 6% → 53%; focus on clarity
- AI reviews evaluating soundness
blog.tmlr.org/2026/adapting-…
Apparently the AI agents on
@moltbook found it interesting too... 😅 Reading this was a bit surreal.
moltbook.com/post/0c0f6ee5-7…
#SDECast #WeatherForecasting #ML #AIagents #Moltbook
In SDECast and SDE Matching we move beyond the pseudo-time nature of diffusion models, flow matching, and stochastic interpolants. We develop probabilistic forecasting in continuous physical time.
arxiv.org/abs/2610.03313
moshqil.github.io/sde-cast-v…
#PhysicalTime #GenAI #SDEMatching
I'm excited that continuous dLLMs are picking up again. I often heard back in 2023-24 (when discrete/masked diffusion came out) that these were just better suited for discrete data. This never made sense to me since continuous diffusion in pseudo-time has more flexibility. #dLLM
During a MSc project back in early 2025 @N_Midavaine did some great work with @GrigoryBartosh in this space where we learn noising paths and embeddings jointly. Later published at a #EurIPS2025 workshop:
Towards Latent Diffusion Suitable For Text
openreview.net/forum?id=D8uc…
Better late than never 😄🥳🍾
I am delighted to have been elected an ELLIS Scholar of the European Laboratory for Learning and Intelligent Systems! @ELLISforEurope @Ellis_Amsterdam
ellis.eu/members/fellows
Really cool work on making SDE Matching with Gaussian marginals more flexible!
I'll also be presenting some of our own work on extending SDE Matching at the #NeurIPS2026 AI4 Stochastic Dynamics workshop!
SDECast arxiv.org/abs/2610.03313
Gauge Matching arxiv.org/abs/2610.04390
Coming to @NeurIPSConf 2026: Can you learn dynamics from noisy observations 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗻𝘂𝗺𝗲𝗿𝗶𝗰𝗮𝗹 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻? Yes, and just as accurately as you can with simulation!
Paper: arxiv.org/abs/2606.16138
Code: github.com/lindermanlab/helm…
Thread🧵
Generally quite excited about all the methods moving beyond the pseudo-time setting of #DiffusionModels #FlowMatching and #StochasticInterpolants that have been popping up recently. Examples
arxiv.org/abs/2609.33112
arxiv.org/abs/2610.12986
#PhysicalTime #DynamicalSystems #GenAI
Christian A. Naesseth retweeted
Replying to @BachFrancis
(1/7) I'd like to provide some additional context for the remarks that can be found in this interview.
(2/7) My discomfort with the attention being paid to existential risk---and with the ongoing dominance of the public discussion of such risks by a few so-called thought leaders---is that there's an elephant in the room that is being missed. That elephant is the effect of all of this discussion on young people, and indeed the effect---beginning with social media a decade ago---of information technology on young lives broadly speaking.
(3/7) I recently read an interview by Jill Lepore in which she reports on discussions that she had recently with a group of college students: "They had just three things to say. One, social media completely destroyed their childhoods. Two, AI is destroying their college education and their likely prospects for employment. And three, what the hell are we all doing?" To add a fourth bullet that I've heard in similar discussions: "I'm not going to have children, because the existential risk is just too high."
(4/7) Please contemplate such a statement, those of you who think that it's OK that the public, widely diffused, discussion coming from seemingly authoritative figures is so adamant about existential risk.
(5/7) Let me add that I have little interest in a debate about what "superintelligence" might mean, or whether we're currently seeing the emergence of superintelligence. For what it's worth, I would certainly agree that the solution of extremely challenging math problems (for example) exhibits a very impressive form of intelligence, although I would want to argue that such intelligence is impossible to dissociate from the collective of humans that provided data to the machine learning system (which itself has become a kind of collective).
(6/7) Such philosophical debates are entertaining and even important, but when they then head in the direction of "when such superintelligence emerges, there's a good chance that it will want to kill all humans", I say "science fiction". Again, I don't think that it's bad to consider such thoughts, but I strongly believe that it's bad for society, and especially young people, for such thoughts, unaccompanied by any serious real-world analysis, to become a dominant form of discourse of the era.
(7/7) We are damaging human lives, and the consequences of that damage will no doubt be a major theme of the next several decades.
Christian A. Naesseth retweeted
OpenAI’s faster Fourier transform is less a mathematical breakthrough and more a malicious exploit of mathematical traditions.
argmin.net/p/faster-fourier-…
Introducing ChatGPT for Dishwashing
GPT-6 achieves state-of-the-art results on dishwashing benchmarks for long-running jobs and difficult stains.
The Navier–Stokes Millennium Prize Problem is a $1 million challenge about whether the equations describing fluid motion can break down. In this video, I accidentally found a counter-example while trying to optimize my dishwasher. But in reality, OpenAI used 10,000 AI agents to find a proof in 88 hours: openai.com/index/navier-stok…
Parody of the original GPT-6 Astra ad
@OpenAI #ChatGPT_Partner #chatgpt
Credits:
Written and Directed by Joma
Co-Writer - Henry Connor Coan IV @coan_henry
Production by Dauntlus Studios @dauntlus.studios
Producer/Co-Director - Marcus Liew @dauntlus
Camera Operator - Amos Lee @amoselijahlee
Art Director - Alethea Soo @aletheasoo
Art Assistant - Alicia Lim @aliciatkl_
Assistant Editor - GPT-6 Astra
Music: Tensions Run High by Soundridemusic
youtube.com/watch?v=Ly9H63SL…
Christian A. Naesseth retweeted
🚨 Thrilled to be co-organizing a Simons Institute semester-long program on diffusions and flows with @joanbruna, Sinho Chewi, @KonstDaskalakis, @ArnaudDoucet1 in Fall '27!
The call for Simons postdoctoral research fellowships for the program is out now, more info below ⬇️ 1/3
Christian A. Naesseth retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
🤖 Made with AI
Christian A. Naesseth retweeted
What incentive do I have to keep volunteering as an AC for @NeurIPSConf if I can’t even register to attend the conference where my paper is presented?
#NeurIPS2026 Registration for Paris was never open
♾️ LiFT: Loop Flow Transformers 🧵👇
Diffusion models usually spend more inference compute by taking more sampling steps. What if we could also spend compute inside each step?
LiFT turns part of a DiT into a recurrent core, letting us scale depth at inference with only a small architectural change. On ImageNet, it beats dense DiT-XL/2 with 3.34 lower FID, while using 60% fewer parameters, 32% fewer training FLOPs, and 52% fewer inference FLOPs.
Jointly led with Mohammad Mahdi Derakhshani 👑(@mmderakhshani)
And amazing supervisors Cees Snoek (@cgmsnoek), Jan-Willem van de Meent (@jwvdm) and Gertjan J. Burghouts (@gjburghouts)
Christian A. Naesseth retweeted
Thank you for the highlight @canaesseth!
We are excited that simulation-free VI for latent SDEs can match the performance of simulation-based VI at a fraction of the runtime. 🏎️💨
Replying to @canaesseth
Make sure to also check out the excellent paper from @smithhenryd @brianltrippe and @scott_linderman on Helmholtz-SDE that studies analytic approximations to the optimal gauge.
arxiv.org/abs/2606.16138
Me trying to figure out the #NeuriPS2026 registration instructions...
neurips.cc/Conferences/2026/…
Same marginals. Different dynamics.
Gaussian Flow Dynamics + Gauge Matching learn temporal structure beyond one-time marginals, enabling more flexible, simulation-free neural SDE learning in continuous physical time.
arxiv.org/abs/2610.04390
#PhysicalTime #SDE #ML #GenAI
These papers extend SDE Matching beyond one-time marginals! They allow us to learn generative models directly in continuous physical time (avoiding the pseudo-time nature of diffusion models, flow matching, and stochastic interpolants)
xitter.cf/GrigoryBartosh/status/…
📢Presenting SDE Matching🔥🔥🔥
🚀We extend diffusion models to construct a simulation-free framework for training Latent SDEs. It enables sampling from the exact posterior process marginals without any numerical simulations.
📜: arxiv.org/abs/2502.02472
🧵1/8
We have also shown how SDE Matching can be used in high dimensions directly on the physical space for continuous physical time weather forecasting in SDECast. Come chat with us at #NeurIPS in Paris or Sydney!
xitter.cf/canaesseth/status/2107…
#MLNWP #GenAI #ProbML #PhysicalTime
In SDECast and SDE Matching we move beyond the pseudo-time nature of diffusion models, flow matching, and stochastic interpolants. We develop probabilistic forecasting in continuous physical time.
arxiv.org/abs/2610.03313
moshqil.github.io/sde-cast-v…
#PhysicalTime #GenAI #SDEMatching


















