My full interview with MLStreetTalk has just been posted. I really enjoyed this conversation! We talk about the bitter lesson, scientific discovery, Bayesian inference, mysterious phenomena, and key principles for building intelligent systems. www.youtube.com/watch?v=M-jT...

Most of the #EurIPS workshops now have their websites online 🙌 A lot of them have active call for participation and/or papers, so if you see something relevant to your field of research please consider submitting! Links for most workshops are available at: eurips.cc/workshops/

Looks like a good candidate paper for the Salon des Refusés at @euripsconf.bsky.social

And lastly, if @neuripsconf.bsky.social would choose to reverse the decisions on the papers affected by space constraints, we would be happy and able to accommodate their presentation

Fuck yeah

I love the Salon des Refusés idea!

I reference data science at the singularity constantly as it's not just a model of why data science blew up, but also how any field or org can organize itself around data, code sharing, and benchmarks: arxiv.org/abs/2310.00865

Our NeurIPS submission arxiv.org/abs/2502.08938 did not get in, but it's one of my favorite papers and I think one of the better papers we've ever put out so I want to highlight it

Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway. We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff! 📝 arxiv.org/abs/2412.06014

For anyone who is spiraling, I definitely recommend www.positive.news for a nice palate cleanser and reminder that there are still things going right despite all the garbage fires

I wrote a response to Thomas Friedman's "magical thinking" on AI here: aiguide.substack.com/p/magical-th...

This is years old at this point. Still very underrated and little known. arxiv.org/abs/2103.15671

Reminded again of Kevin Murphy's excellent RL overview: arxiv.org/abs/2412.05265 A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else

Possibly one of the best PhD programs in the world if you are passionate about machine learning and AI:

🚨AISTATS workshop proposals open! Big News: For the first time, there will be a day of workshops at #AISTATS 2026, in Tangier, Morocco 🌴🇲🇦 Quentin Berthet @qberthet.bsky.social and I are workshop chairs. virtual.aistats.org/Conferences/... Deadline: Oct 17, AOE

Let's push for the obvious solution: Dear @neuripsconf.bsky.social ! Allow authors to present accepted papers at EurIPS instead of NeurIPS rather than just additionally. Likely, at least 500 papers would move to Copenhagen, problem solved.

Agustinus is hiring! A great place to start a research journey.

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.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu eurips.cc

Ruining art with Gemini 2.5 Flash. (These are all the prompts, in their entirety) "make this painting less gloomy" "it is still pretty disturbing, make it less gloomy emotionally" "even less gloomy"

We are excited to bring #EurIPS 2025 to Copenhagen in December. Consider becoming a sponsor and support us in making this inaugural event a success! Sponsorship packages are available and can be further customized if necessary. Reach out if you have any questions ❔ Info: eurips.cc/become-spons...

Regardless of whether you plan to use them in applications, everyone should learn about Gaussian processes, and Bayesian methods. They provide a foundation for reasoning about model construction and all sorts of deep learning behaviour that would otherwise appear mysterious.

Fixed it for you...

Fun facts: the Pizza theorem 🍕 states that if Alice and Bob cut a pizza in 4k slices (for k≥2) and take alternating slices, they'll get the same amount even if the cutting wasn't centered. It was proven by Upton in 1968. Before that, nobody knew how to cut pizza. en.m.wikipedia.org/wiki/Pizza_t...

The GOAT of comedic song writing (and performing)! May his memory be a blessing and a reminder of the joy of brilliant silliness (e.g., my personal favorite: "Lobachevsky" www.youtube.com/watch?v=IL4v...)

📢 Present your NeurIPS paper in Europe! Join EurIPS 2025 + ELLIS UnConference in Copenhagen for in-person talks, posters, workshops and more. Registration opens soon; save the date: 📅 Dec 2–7, 2025 📍 Copenhagen 🇩🇰 🔗eurips.cc #EurIPS @euripsconf.bsky.social‬

I agree with most ideas here, but would like to make a different point: It's true that "science has always been a bit shit", but it's still been very effective at improving the human condition. So I don't think it needs to be perfect, "a bit shit" science is still much better than no science at all.

What is common knowledge in your field, but shocks outsiders? We don't agree on what probability actually is. Also, it's not real. Probably...

This morning at #RLDM I talked about Memory Traces, a simple representation for POMDPs that’s probably good at remembering old observations. arxiv.org/abs/2503.15200

This exists! www.boringreport.org

To spice up the debate, does anyone want to volunteer some examples of this?

Give us your silenced, your defunded, Your huddled masses yearning to research freely

Aleatoric and epistemic uncertainty are clear-cut concepts, right? ... right? 😵‍💫 In our new ICLR blogpost we let different schools of thought speak and contradict each other, and revisit chatbots where “the character of aleatory ‘transforms’ into epistemic” iclr-blogposts.github.io/2025/blog/re...

If you are at AISTATS this week, check out our paper on cost-aware simulation-based inference!

New paper accepted to ICML! We present a novel policy optimization algorithm for continuous control with a simple closed form which generalizes DDPG, SAC etc. to generic stochastic policies: Wasserstein Policy Optimization (WPO).

Congratulations to the #AABI2025 Proceedings Track Best Paper Award recipients!

Congratulations to the #AABI2025 Workshop Track Outstanding Paper Award recipients!

We concluded #AABI2025 with a panel discussion on **The Role of Probabilistic Machine Learning in the Age of Foundation Models and Agentic AI** Thanks to Emtiyaz Khan, Luhuan Wu, and @jamesrequeima.bsky.social for participating!

[email protected] gave the third invited talk of the day at #AABI2025! **LLM Processes**

I’m greatly enjoying the setting of this year’s #AABI symposium, thanks to NTU Singapore for hosting us!

Luhuan Wu is giving the second invited talk of the day at #AABI2025! **Bayesian Inference for Invariant Feature Discovery from Multi-Environment Data** Watch it on our livestream: timrudner.com/aabi2025!

Emtiyaz Khan is giving the first invited talk of the day at #AABI2025!

We just kicked off #AABI2025 at NTU in Singapore! We're livestreaming the talks here: timrudner.com/aabi2025! Schedule: approximateinference.org/schedule/ #ICLR2025 #ProbabilisticML

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

1/ If you are at ICLR / AABI / AISTATS, check out work from our lab and collaborators on *inference everywhere anytime all at once*! Go talk to my incredible PhD students @huangdaolang.bsky.social & @chengkunli.bsky.social + amazing collaborator Severi Rissanen. @univhelsinkics.bsky.social FCAI

At #ICLR2025, #HelmholtzMunich researchers are sharing advancements in #MachineLearning. 👉 t1p.de/8jfgn @fabiantheis.bsky.social @carstenmarr.bsky.social @stes.io @zeynepakata.bsky.social @ericschulz.bsky.social @vincefort.bsky.social @iclr-conf.bsky.social

Volume 258 proceedings.mlr.press/v258/ Proceedings of AISTATS 2025 Is now available on PMLR.

In the honored tradition of people who have wifi on a plane, I will exclusively use it to let you know that I'm currently on a plane and have wifi here.

Arriving in Singapore this afternoon 🛬 I'll attend #ICLR2025, #AABI2025, and #AISTATS2025 together with many of my students and collaborators to present our 2 orals, 5 posters, and 14 workshop contributions 🚀 Feel free to drop by!