Peter Prettenhofer

[Oier Mees @oier_mees]

📣 𝗧𝗵𝗿𝗶𝗹𝗹𝗲𝗱 𝘁𝗼 𝗵𝗼𝘀𝘁 𝗗𝗶𝗲𝘁𝗲𝗿 𝗙𝗼𝘅 (@fox_dieter17849) 𝗳𝗼𝗿 𝗮 𝗴𝘂𝗲𝘀𝘁 𝗹𝗲𝗰𝘁𝘂𝗿𝗲 𝗮𝘁 𝘁𝗼𝗱𝗮𝘆'𝘀 𝘀𝗲𝘀𝘀𝗶𝗼𝗻 𝗼𝗳 𝗥𝗼𝗯𝗼𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴: 𝗙𝗿𝗼𝗺 𝗙𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹𝘀 𝘁𝗼 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 𝗮𝘁 @ETH!
Today's speaker almost needs no introduction. Dieter is Professor at the @UW and Senior Research Director at @allen_ai, co-author of the landmark textbook 𝗣𝗿𝗼𝗯𝗮𝗯𝗶𝗹𝗶𝘀𝘁𝗶𝗰 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀, Fellow of @IEEEorg, @RealAAAI, and @TheOfficialACM, and recipient of the 𝟮𝟬𝟮𝟬 𝗜𝗘𝗘𝗘 𝗣𝗶𝗼𝗻𝗲𝗲𝗿 𝗶𝗻 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗮𝗻𝗱 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻 𝗔𝘄𝗮𝗿𝗱 and the 𝟮𝟬𝟮𝟯 𝗜𝗝𝗖𝗔𝗜 𝗝𝗼𝗵𝗻 𝗠𝗰𝗖𝗮𝗿𝘁𝗵𝘆 𝗔𝘄𝗮𝗿𝗱.
Today he will be talking about: "𝗧𝗼𝘄𝗮𝗿𝗱 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗖𝗼𝗺𝗽𝗲𝘁𝗲𝗻𝘁 𝗥𝗼𝗯𝗼𝘁𝘀" 🤖
His talk will cover large-scale data generation for robot manipulation, the role of simulation and sim-to-real transfer, and ongoing work at Ai2 on training models that are genuinely competent across a broad set of tasks — moving beyond narrowly trained, disconnected skills 🚀
If you are in Zürich and want to join us:
📍 Where: Room NO C 60, Sonneggstrasse 5
🕓 When: Today, May 18, 17:00 – 18:00
See you there!

[Nikolaus West @NikolausWest]

https://t.co/JJfRVbd2OG

[Peter Holderrieth @peholderrieth]

🚀MIT Flow Matching and Diffusion Lecture 2026 Released (https://t.co/bKgs2wghvY)!

We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include:
📺 Videos: Step-by-step derivations.
📝 Notes: Mathematically self-contained lecture notes
💻 Coding: Hands-on exercises for every component

We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models.

Everything is available here: https://t.co/bKgs2wghvY

A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints!

#MachineLearning #GenerativeAI #MIT #DiffusionModels #AI

[Olivier Grisel @ogrisel]

Very pleased by the recent work done by @hug_nicolas to speed-up our pure Python + @numba_jit prototype implementation of gradient boosted trees: https://t.co/Ii6bAqmoRa The master branch is now competitive with LightGBM on the Higgs boson benchmark dataset.

[Gael Varoquaux 🦋 @GaelVaroquaux]

Announcing IMPAC: an IMaging-PsychiAtry Challenge, using data-science to predict autism from brain imaging
https://t.co/BjayWTTmz4

9000€ of prizes to win! More than 2000 individuals scanned!

Organized by @SaclayCDS and @R3RT0's team at @institutpasteur

[Peter Prettenhofer @pprett]

@amuellerml @twiecki https://t.co/m1hpxAN20R says its not possible for pystan2 but will be addressed via a refactor in pystan3 (see https://t.co/HRLprkDv7o )

[Mike Bostock @mbostock]

Don’t compare percentage change on a linear scale; use a log scale instead. -50% (0.5×) is as big a change as +100% (2×).

[Alessandro Suglia @ale_suglia]

More effective convergence guarantees with AMSGrad, best paper award @ICLR18. Thanks to a slight change in ADAM we can get a stronger update rule for Gradient Descent methods. https://t.co/uGBN8vgDLz #dlearn #Optimization

[David Mimno @dmimno]

Maybe now I will remember

[Gilles Louppe @glouppe]

Tomorrow I'll actually teach my first ever lecture on deep learning, rebuilding all the basic constructs, starting from LDA up to deep rectified networks. Lecture slides available at https://t.co/9EprnOp37I

[Nein. @NeinQuarterly]

Worry, if you must, about the future. But you can take comfort in knowing there’s less of it every day.

[Antoine Miech @antoine77340]

The hype of being an AI research scientist nowadays.

[Travis Oliphant @teoliphant]

. @ContinuumIO we have changed our name to Anaconda, Inc. We are more committed than ever to community: https://t.co/TDxGKpSIzP

[Tianqi Chen @tqchenml]

I am proud to announce TVM, our new deep learning compiler toolchain https://t.co/lIPoX0FPXL https://t.co/KsPmVEF1pg @guestrin @uwcse

[Andreas Mueller @amuellerml]

We just released scikit-learn 0.19. Update with pip or conda. A big thank you to everybody who contributed! https://t.co/rkytflTGu3

[Mathieu Blondel @mblondel_ml]

Nice example of time-series averaging using soft-DTW https://t.co/2b9bW4WSro Part of tslearn by Romain Tavenard

[Thomas Wiecki @twiecki]

New post: Random-Walk #Bayesian Deep Networks: Dealing with Non-Stationary Data https://t.co/hcTBjump34 With animations! #PyMC3

[Olivier Grisel @ogrisel]

ELI5: debug and explain the behavior of Python Machine Learning models: https://t.co/Lsq4VkM9Xb (sklearn, xgboost, lightning, crfsuite....)

[Olivier Grisel @ogrisel]

Stochastic online matrix factorization in cython with sklearn compatible API by @arthurmensch: https://t.co/CdFD67wo5e dict learning & nmf