George Papamakarios

192 posts

George Papamakarios

George Papamakarios

@gpapamak

Research Scientist @GoogleDeepMind, working on Gemini pretraining

London, England Katılım Aralık 2017
392 Takip Edilen2.6K Takipçiler
Sabitlenmiş Tweet
George Papamakarios
George Papamakarios@gpapamak·
Check out our extensive review paper on normalizing flows! This paper is the product of years of thinking about flows: it contains everything we know about them, and many new insights. With @eric_nalisnick, @DeepSpiker, @shakir_za, @balajiln. arxiv.org/abs/1912.02762 Thread 👇
Danilo J. Rezende@DaniloJRezende

Looking for something to read in your flight to #NeurIPS2019? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) arxiv.org/abs/1912.02762 with @gpapamak @eric_nalisnick @DeepSpiker @balajiln @shakir_za

English
3
158
630
0
George Papamakarios retweetledi
Theo Weber
Theo Weber@theophaneweber·
Interested in a project at the intersection of large language models, self-improvement, reasoning + tool use, and computer security / code vulnerability? Our project is looking for a student researcher in that area (position is in London)! Please reach out and apply at google.com/about/careers/…
English
0
9
26
9.5K
George Papamakarios retweetledi
Shimon Whiteson
Shimon Whiteson@shimon8282·
I was recently on a panel with several other professors and we were asked to give some tips to graduate students in machine learning. It got me thinking about why professors are so bad at giving advice. So here are some reasons why you should not take advice from professors.
English
12
260
1.4K
1.6M
George Papamakarios
George Papamakarios@gpapamak·
Happy to share new work in #AI4Science Gibbs free energies via isobaric-isothermal flows arxiv.org/abs/2305.13233 In previous work we proposed a flow model that generates crystals at constant volume – this one handles the (harder) case of varying volume at constant pressure
English
1
6
56
8.4K
George Papamakarios
George Papamakarios@gpapamak·
📢 New paper on diffusion models for simulation-based inference, to appear at #ICML2023 arxiv.org/abs/2209.14249 tl;dr: Diffusion models are great for SBI: using a trick akin to classifier-free guidance, they let you do inference with more observations than you trained on 🙂
English
3
26
162
26.4K
George Papamakarios retweetledi
Ricky T. Q. Chen
Ricky T. Q. Chen@RickyTQChen·
Excited to share our new work on Riemannian Flow Matching. Unlike diffusion-based approaches, it’s - completely simulation-free on simple manifolds, - trivially applies to higher dimensions, - tractably generalizes to general geometries! arxiv.org/abs/2302.03660 w/ @lipmanya
GIF
English
6
69
366
86.1K
George Papamakarios retweetledi
Hyunjik Kim
Hyunjik Kim@hyunjik11·
Previously we had introduced *functa*, a framework for representing data as neural functions (aka neural fields, INRs) and doing deep learning on them. In our recent work *spatial functa* we show how to scale up the approach to ImageNet-1k 256x256. 📝arxiv.org/abs/2302.03130
Hyunjik Kim tweet media
Hyunjik Kim@hyunjik11

Ever wondered why deep learning is always done on array data?🤔 Happy to announce our work: From data to functa: Your data point is a function and you can treat it like one 📝arxiv.org/abs/2201.12204 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22

English
1
36
176
48.4K
George Papamakarios retweetledi
Kevin Patrick Murphy
Kevin Patrick Murphy@sirbayes·
I am delighted to announce that the "real" camera-ready version of my new book, "Probabilistic Machine Learning: Advanced Topics", is now available. It will appear in print this summer, but it is already freely available online at probml.github.io/book2.
English
19
416
2.1K
328.3K
George Papamakarios retweetledi
Machine Learning: Science and Technology
Machine Learning: Science and Technology@MLSTjournal·
DRUM ROLL🥁... announcing the #MOSTREAD @MLSTjournal article in 2022 with 9617 downloads! 'Normalizing #flows for atomic solids' by @PeteWirnsberger @gpapamak @BlundellCharles @sracaniere et al @DeepMind -bit.ly/3PqmHeJ #machinelearning #statphys #compchem #materials #AI
Machine Learning: Science and Technology tweet media
Machine Learning: Science and Technology@MLSTjournal

🥳👏Beginning our countdown of the top 10 most read @MLSTjournal articles published in 2022 - #10 coming up! #MachineLearning #compchem #neuralnetworks #datascience #AI #quantum #materials #drugdiscovery #HPC #DeepLearning #compbio #bioinformatics #HEP #openscience #cosmology

English
0
5
19
9.4K
George Papamakarios retweetledi
Hyunjik Kim
Hyunjik Kim@hyunjik11·
We're organizing an #ICLR2023 workshop titled: 🌟Neural Fields across Fields: Methods and Applications of Implicit Neural Representations🌟 sites.google.com/view/neural-fi… Please submit your cool research (due: 3rd Feb)! Looking forward to seeing you on 05/05/23 @ Kigali, Rwanda 🇷🇼
English
1
24
115
35.1K
Bennet Leff
Bennet Leff@BennetLeff·
@gpapamak Hi! Cool work! Do you think there's significance in that the algorithms performed typically have an underlying graph structure and the model being a GNN?
English
1
0
0
0
George Papamakarios
George Papamakarios@gpapamak·
Happy to share our latest work: "A Generalist Neural Algorithmic Learner" A single graph neural network that learns to execute 30 different algorithms: sorting, searching, string matching, etc Challenging multi-task & generalization problem where inductive biases are important
Google DeepMind@GoogleDeepMind

Introducing a generalist neural algorithmic learner, capable of carrying out 30 different reasoning tasks, with a 𝘴𝘪𝘯𝘨𝘭𝘦 graph network. These include: 🔵 Sorting 🔵 Shortest paths 🔵 String matching 🔵 Convex hull finding And more: dpmd.ai/3FC1FqA

English
1
7
37
0
George Papamakarios retweetledi
Max Dax
Max Dax@maximilian_dax·
Can you trust deep learning for scientific inference? And what can you do when results are inaccurate? We address these questions for ML-based inference of complex gravitational wave models and get highly accurate and reliable results. arxiv.org/abs/2210.05686 1/12
GIF
English
3
63
237
0
George Papamakarios retweetledi
Matej Balog
Matej Balog@matejbalog·
Happy to share our new paper in @Nature on using Deep Reinforcement Learning for discovering new, faster algorithms to multiply matrices: dpmd.ai/nature-alpha-t… #AlphaTensor More in thread👇(1/n)
Google DeepMind@GoogleDeepMind

Today in @Nature: #AlphaTensor, an AI system for discovering novel, efficient, and exact algorithms for matrix multiplication - a building block of modern computations. AlphaTensor finds faster algorithms for many matrix sizes: dpmd.ai/dm-alpha-tensor & dpmd.ai/nature-alpha-t… 1/

English
4
15
53
0

Keşfet

@IsomorphicLabs @GoogleDeepMind @nanliuuu @icmlconf @inve_michele @pimdehaan @FrankNoeBerlin @tomasgeffner