Picture

Mark van der Wilk @markvanderwilk

Associate Professor in Machine Learning at the University of Oxford. Interested in automatic inductive bias selection using Bayesian tools. mvdw.uk Oxford, UK Joined November 2014
  • Tweets
    385
  • Followers
    4K
  • Following
    596
  • Likes
    2K
Mark van der Wilk retweeted
dhir_anish Profile Picture

Anish Dhir @dhir_anish

5 months ago

Understanding causes is key to science. Finite observational data alone isn't enough. While Bayes offers a framework to deal with this, the calculations are often intractable. We introduce a method to accurately approximate the posterior over causal structures. #ICLR2025 🧵1/15

Mark van der Wilk retweeted
dhir_anish Profile Picture

Anish Dhir @dhir_anish

5 months ago

Excited to be presenting this work at #ICLR2025. Please do reach out if you are interested in a similar space! 🗓️: Hall 3 + Hall 2B #471 🕐: Fri 25 Apr, 3 p.m. 📜: openreview.net/forum?id=eeJz7… This was a great collaboration w/ @_MatthewAshman, @jamesrequeima, @markvanderwilk

Mark van der Wilk retweeted
mark_cummins Profile Picture

Mark Cummins @mark_cummins

8 months ago

After using Deep Research for a while, I finally get the "it's just slop" complaint people have about AI art. Because I don't care much about art, most AI art seems pretty good to me. But information is something where I'm much closer to a connoisseur, and Deep Research is just…

Mark van der Wilk retweeted
mpshanahan Profile Picture

Murray Shanahan @mpshanahan

8 months ago

I agree with @AmandaAskell. It is a fallacy. It can be appropriate to say both a) that LLMs are next-token predictors, at a mechanistic level, and b) that they have understanding, at another level. (a) is an engineering fact. But the negation of (b) does not follow. 1/2

GaryMarcus Profile Picture

Gary Marcus @GaryMarcus

8 months ago

I agree with @AmandaAskell. It is a fallacy. It can be appropriate to say both a) that LLMs are next-token predictors, at a mechanistic level, and b) that they have understanding, at another level. (a) is an engineering fact. But the negation of (b) does not follow. 1/2

Mark van der Wilk retweeted
AjdDavison Profile Picture

Andrew Davison @AjdDavison

9 months ago

I'm recruiting a new PhD student on Gaussian Belief Propagation for Spatial AI. For this particular opportunity: 1. The funding I have is only available to a student who qualifies for "home fees" in England; 2. I'm looking for someone who can start soon, ideally April 2025.

Mark van der Wilk retweeted
tolga_birdal Profile Picture

Tolga Birdal @tolga_birdal

10 months ago

Within 2025, I will be hiring several PhD candidates and Postdoctoral researchers @ICComputing to work on various aspects of #TopologicalDeepLearning (#TDL). Posts are attached. The postdoc positions are also available to apply under: imperial.ac.uk/jobs/search-jo… #CVPR #CVML #AI #ML

Mark van der Wilk retweeted
wooldridgemike Profile Picture

Michael Wooldridge @wooldridgemike

a year ago

Simultaneously funny and very relevant question… (Answer: no it doesn’t. But what’s missing, exactly?)

alexisgallagher Profile Picture

Alexis Gallagher @alexisgallagher

a year ago

Simultaneously funny and very relevant question… (Answer: no it doesn’t. But what’s missing, exactly?)

markvanderwilk Profile Picture

Mark van der Wilk @markvanderwilk

a year ago

Test sets are the "get out of jail free" card of ML. It allows us to apply any crazy statistically-unprincipled method, and simply check if the predictions are good. But, it's easy to forget that holdout estimates themselves rely on assumptions that can be violated in practice!

beenwrekt Profile Picture

Ben Recht @beenwrekt

a year ago

Test sets are the "get out of jail free" card of ML. It allows us to apply any crazy statistically-unprincipled method, and simply check if the predictions are good. But, it's easy to forget that holdout estimates themselves rely on assumptions that can be violated in practice!

markvanderwilk Profile Picture

Mark van der Wilk @markvanderwilk

a year ago

Looking forward to #GenU2024, my favourite gathering in the AI/ML calendar. The talks again all look incredibly interesting!

jesfrellsen Profile Picture

Jes Frellsen @jesfrellsen

a year ago

Looking forward to #GenU2024, my favourite gathering in the AI/ML calendar. The talks again all look incredibly interesting!

Mark van der Wilk retweeted
KevinKaichuang Profile Picture

Kevin K. Yang 楊凱筌 @KevinKaichuang

a year ago

A Gaussian Process regression model built on top of protein language model embeddings and inverse folding models makes accurate predictions with calibrated uncertainties. @WouterBoomsmaDK

Trends for United States

Dodgers
88,5 B posts
Roki
8.742 posts
Reds
35,8 B posts
#AEWDynamite
33,5 B posts
Mookie
5.841 posts
Yamamoto
20,8 B posts
Tito
12,5 B posts
Lodolo
1.844 posts
Andrade
20,6 B posts
Elly
7.620 posts
Sheehan
2.032 posts
Harmless
9.040 posts
#Survivor49
3.150 posts
#GhostofYotei
11,3 B posts
#LoveIsBlind
1.844 posts
Jane Goodall
200 B posts
Two Delta
5.110 posts
Billy Jack
Nick Martinez
Game 3
51,9 B posts

You might like

Max Welling
@wellingmax
39K Followers
VP Research, Google DeepMind, ex-head of Google Brain. Professor at University of Cambridge. Machine Learning Researcher. ex-Chief Scientist & VP of AI, Uber.
Zoubin Ghahramani
@ZoubinGhahrama1
32K Followers
Professor of Computer Science at Oxford. Senior Staff Research Scientist at Waymo.
Shimon Whiteson
@shimon8282
18K Followers
Machine Learning Group @Cambridge_Uni
Cambridge MLG
@CambridgeMLG
6K Followers
AI Prof @Stanford | CEO & Cofounder @InceptionAILabs | Co-inventor of DDIM, FlashAttention, DPO, GAIL, and score-based/diffusion models
Stefano Ermon
@StefanoErmon
20K Followers
@AnthropicAI. Prev. @Google Brain/DeepMind, founding team @OpenAI. Computer scientist; inventor of the VAE, Adam optimizer, and other methods. ML PhD.
Durk Kingma
@dpkingma
50K Followers
Associate Professor in Machine Learning at the University of Oxford, Head of RainML Research Lab (https://t.co/uuBwQ2WdMN)
Tom Rainforth
@tom_rainforth
6K Followers
Professor in Machine Learning, Gatsby Computational Neuroscience Unit Research Scientist, Google DeepMind https://t.co/JJNqmn7jak
Arthur Gretton
@ArthurGretton
11K Followers
Professor of Machine Learning, University of Oxford @OATML_Oxford Group Leader Director of Research at the UK govt's AI Security Institute (AISI)
Yarin
@yaringal
41K Followers
Professor of Machine Learning, University of Cambridge, UK.
Jose Miguel Hernánde...
@jmhernandez233
5K Followers
teaching machines🤖 to learn🔍 and fantasize🪄 now 🇬🇧@ImperialCollege @ICComputing ex @MSFTResearch @CambridgeMLG helping @aistats_conf 24-26
yingzhen
@liyzhen2
4K Followers
ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days! BTW you should go find me on another website where i post more actively
Gergely Neu
@neu_rips
11K Followers
Senior Staff Research Scientist @GoogleDeepMind, previously Oxford Stats Prof - interested in Comp Stats, Generative Modeling, Monte Carlo, Optimal Transport
Arnaud Doucet
@ArnaudDoucet1
6K Followers
Assistant prof at ISTA. Prev: AWS, PhD at ETH Zürich/Max Planck Institute for Intelligent Systems.
Francesco Locatello
@FrancescoLocat8
5K Followers
ML research @Apple, prev @OxCSML @InfAtEd, part of @MLinPL & @polonium_org 🇵🇱, sometimes funny
Adam Golinski
@adam_golinski
3K Followers