Justin Gilmer @jmgilmer
Research Scientist at Google Brain. Joined June 2014-
Tweets54
-
Followers1K
-
Following128
-
Likes33
Happy to share that our #MLOps paper "Improving Training Stability for Multitask Ranking Models in Recommender Systems" got accepted to KDD 2023 🎉 arxiv.org/abs/2302.09178 Joint work between Google DeepMind (@edchi, @jmgilmer and others) and YouTube. Link to code below. 🧵
1/ There is a huge headroom for improving capabilities of our vision models and given the lessons we've learned from LLMs, scaling is a promising bet. We are introducing ViT-22B, the largest vision backbone reported to date: arxiv.org/abs/2302.05442
(6/6) ...sin embargo no se ha probado que converja a algún número. Lo que sí se sabe (lo probó Justin Gilmer @jmgilmer en 2013), es que la densidad de números felices está acotada entre 0.1138 y 0.18577. degruyter.com/document/doi/1…
I often get asked for advice on breaking into a machine learning role. Here's a short post, in case it helps you. varungodbole.github.io/2022/09/18/bre…
I finally found time to put my PhD thesis on arxiv. Check it out! Thanking everyone who made this thesis possible 🖤🎊 arxiv.org/abs/2104.12053
This 2019 paper on Fourier analysis of adversarial robustness, by Dong Yin et al., is really worth a look. It gives a simple, intuitive way of understanding a wide variety of adversarial and robustness phenomena. papers.nips.cc/paper/9483-a-f…
Check out our new paper on adversarial robustness as a prior for better transfer learning! A great colab w/ @andrew_ilyas @logan_engstrom @akapoor_av8r @aleks_madry We open-source ~70 robust ImageNet models which you might find helpful! github.com/microsoft/robu…
Check out our new paper on adversarial robustness as a prior for better transfer learning! A great colab w/ @andrew_ilyas @logan_engstrom @akapoor_av8r @aleks_madry We open-source ~70 robust ImageNet models which you might find helpful! github.com/microsoft/robu…
Every day a new Y-axis extension for the country without a plan New cases beget new cases, hospitalizations, chronic illness, and deaths. That demands serious, aggressive action to intervene.
Very thought-provoking talk by Justin Gilmer at the #ICML2020 UDL workshop. Adversarial examples are just a case of out-of-distribution error. There is no particular reason to defend against the nearest OOD error (i.e., L-infty adversarial example) 1/
Eric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pKevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.rohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.Delip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈David Pfau @pfau
22K Followers 1K Following Knowledge manifests itself in radiant dreams that shimmer like the wild sun Views are my own pfau at sigmoid dot social on 🦣 https://t.co/xqtVHHVI17 on 🦋Zachary Nado @zacharynado
5K Followers 648 Following Research engineer @googlebrain. Past: software intern @SpaceX, ugrad researcher in @tserre lab @BrownUniversity. All opinions my own.Jeremy Cohen @deepcohen
4K Followers 867 Following PhD student in machine learning at Carnegie Mellon. The goal of my research is to turn deep learning into a real engineering discipline.Aakanksha Chowdhery @achowdhery
7K Followers 3K Following LLMs @ Google DeepMind :: PaLM, Gemini // Previously @MSFTResearch, @Stanford, @Princeton // views my own and subject to changeSara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.Jeff Dean (@🏡) @JeffDean
296K Followers 6K Following Chief Scientist, Google DeepMind and Google Research. Co-designer/implementor of things like @TensorFlow, MapReduce, Bigtable, Spanner, Gemini .. (he/him)Michael Bronstein @mmbronstein
43K Followers 4K Following #DeepMind Professor of #AI @UniofOxford / Fellow @ExeterCollegeOx / ML Lead @ProjectCETI / https://t.co/kZpGpDzYeVAndrew Carr (e/🤸) @andrew_n_carr
15K Followers 3K Following science @getcartwheel AI writer @tldrnewsletter advisor @arcade_ai Past - Codegen @OpenAI, Brain @GoogleAI, world ranked Tetris playerBen Poole @poolio
17K Followers 1K Following research scientist at google brain. phd in neural nonsense from stanford.Nathan Benaich @nathanbenaich
51K Followers 32K Following solo member of investment staff @airstreet, brewing ambition @airstreetcafe, next token predictor @airstreetpressSoumith Chintala @soumithchintala
185K Followers 877 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.Makya @Makya12345678
5 Followers 963 Followingpadma reddy @padmareddy34726
162 Followers 4K FollowingRag @Beingsissyphus1
3 Followers 86 FollowingAnkush Garg @agbgarg
27 Followers 125 FollowingYi-Tsai Liang @sgsguietsu2
13 Followers 107 FollowingDiana_DFG @DianaDFG11164
1 Followers 497 Following Nice to meet you. My hobbies are reading, food and sports. I like cats😘 I like to meet new friends while traveling🎉🎉🎉Shreya Kapoor @SKapoor_18
321 Followers 1K Following PhD @CogCoVi |Formerly Data Scientist @MPI-CBS| https://t.co/HWJLt7Jhwk. Life Science Informatics @UniBonnAndrew white @Andreww95636515
129 Followers 3K Following 3d modeling. Gaussian splatting, NeRF, Diffusion models, GANs.Pablo Pernías @pabloppp
831 Followers 658 Following Making some dreams become realities... AI, DL, ML, CV, Generative Models, Magic ✨Eva Louise Marie Gabr.. @e681554349
7 Followers 3K FollowingAdam Falls @AdamFalls172137
57 Followers 963 Following양소리(梁素莉) @yangsoli68695
19 Followers 1K FollowingJingfeng Wu @uuujingfeng
757 Followers 908 Following Postdoc @SimonsInstitute @UCBerkeley; alumnus of @JohnsHopkins @PKU1898; deep learning theory, optimization, and statistical learning.Vaibhav Kumar @vaibhavk97
3K Followers 1K Following AI @Replit | Ex-@Amazon @Microsoft | @georgiatech | Tweets reflect my own viewsKonstantinos Babalis @babaliskonstan1
54 Followers 650 Following Mathematics @ Birkbeck, University of Londonstvhuang @_stvhuang
0 Followers 610 FollowingPavel @pkartaviy
3 Followers 62 FollowingUnbox Research @unboxresearch
745 Followers 648 Following We write articles about AI! https://t.co/YfdaFwMP2d We’re a machine learning research & development company. We find answers in data. Founded by @tylerneylon.kandarp joshi @KANDARPRJOSHI
9 Followers 301 FollowingLilliana Kinnebrew @LKinnebrew50535
45 Followers 5K FollowingSahasra Keerthi @sahasra_keerthi
18 Followers 157 Followingsuper intelligence @eacc72
12 Followers 663 Following GPT6 is a Level 2 AGI and will be released in 2025Robin Rombach @robrombach
6K Followers 397 Following Generative enthusiast and long-term PhD Student @LMU_Muenchen. Author of VQGAN, Latent Diffusion, Stable Diffusion.Eric Auld @AuldEric
314 Followers 673 Following AI, math, CS. Former @uclamath. I’ll let you be in my dream if I can be in yoursOle Jonas @friendly_tweedy
54 Followers 499 FollowingBurny — Effective O.. @burny_tech
14K Followers 5K Following Transhuman engineer in singularity! Lover of AI and omnidisciplionary metamathemagics! Hypercuriousia! Omniperspectivity! Freedom, growth, flourishing for all!Tuan Vu @VuAhnTuan
323 Followers 1K FollowingIf useful, I pass alo.. @igniteyourmagic
383 Followers 2K Following On a mission to explore and share life’s lessons. Follow to join me on this enlightening journey. No clickbait, no nonsense. If useful, I pass along. 💡📝💬FOCAL Lab@UIUC @uiuc_focal_lab
42 Followers 74 Following FOrmally Certified Automation and Learning (FOCAL) Lab at the University of Illinois Urbana-ChampaignStefani Karp @StefaniKarp
19 Followers 2K FollowingHannah Rana @spacehannahr
161 Followers 270 Following Scientist @NASA @Caltech | 2022 @SchmidtFellows @Harvard @CenterForAstro | Research Lead @NeutronStarSys | 30U30 @Forbes | Prev @esa @cern @UniofOxfordMircea Mironenco @mirceamironenco
79 Followers 1K FollowingOlioli @Oliolilyx
125 Followers 2K FollowingJiashu Xu @JiashuXu2
132 Followers 612 Following First-year graduate student at @Harvard; Undergrad at @USCant0ine @ant0ine___
0 Followers 324 Followingpushkarini agharkar @p_agharkar
22 Followers 25 FollowingRong Ching Chang @AnnCC12
677 Followers 5K Following Fascinated by ML, LLMs, GNN, Multimodal models in social media. Ph.D. student @ucdavisxlcizor @xlcizor
88 Followers 380 FollowingKrishna Balasubramani.. @krizna_b
256 Followers 387 Following Associate professor at @ucdavis #machinelearning #deeplearning #probability #statistics #optimization #samplingAndrej Karpathy @karpathy
978K Followers 904 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Eric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pDan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)Zachary Nado @zacharynado
5K Followers 648 Following Research engineer @googlebrain. Past: software intern @SpaceX, ugrad researcher in @tserre lab @BrownUniversity. All opinions my own.Jeremy Cohen @deepcohen
4K Followers 867 Following PhD student in machine learning at Carnegie Mellon. The goal of my research is to turn deep learning into a real engineering discipline.Zoubin Ghahramani @ZoubinGhahrama1
24K Followers 615 Following VP Research, Google DeepMind, ex-head of Google Brain. Professor at University of Cambridge. Machine Learning Researcher. ex-Chief Scientist & VP of AI, Uber.Sara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.Jeff Dean (@🏡) @JeffDean
296K Followers 6K Following Chief Scientist, Google DeepMind and Google Research. Co-designer/implementor of things like @TensorFlow, MapReduce, Bigtable, Spanner, Gemini .. (he/him)Thomas G. Dietterich @tdietterich
50K Followers 505 Following Distinguished Professor (Emeritus), Oregon State Univ.; Former President, Assoc. for the Adv. of Artificial Intelligence; Robust AI & Comput. SustainabilityIlya Sutskever @ilyasut
370K Followers 2 Following towards a plurality of humanity loving AGIs @openaiBen Poole @poolio
17K Followers 1K Following research scientist at google brain. phd in neural nonsense from stanford.Boaz Barak @boazbaraktcs
17K Followers 418 Following Computer Scientist. See also https://t.co/EXWR5k634w, https://t.co/SEVX6it6z3 ( @[email protected] , boaz.barak in threads ). Opinions my own.Jascha Sohl-Dickstein @jaschasd
19K Followers 623 Following Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.Richard Socher @RichardSocher
101K Followers 971 Following CEO @youSearchEngine Investing at @aixventuresHQ Before: Stanford Adj Prof in AI/NLP, Chief Scientist at Salesforce, MetaMindBen Recht @beenwrekt
26K Followers 363 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.Sebastian Borgeaud @borgeaud_s
991 Followers 259 Following Research Engineer at DeepMind with a focus on Large Language Models and large scale Deep LearningElvis Dohmatob @dohmatobelvis
3K Followers 522 Following Machine learning researcher @MetaAI. Previously @Criteo and @Inria. I tweet on math, ML, and lots of random stuff. Tweets are mine. Blog: https://t.co/XAsL4l6Q7Oriol Vinyals @OriolVinyalsML
166K Followers 82 Following VP of Research & Deep Learning Lead, Google DeepMind. Gemini co-lead. Past: AlphaStar, AlphaFold, AlphaCode, WaveNet, seq2seq, distillation, TF.George Tucker @georgejtucker
6K Followers 179 Following Researcher at Google Brain, thinking about RL and sequence modelsChristopher Manning @chrmanning
126K Followers 115 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋Lisha @lishali88
16K Followers 919 Following Make games with @rosebud_ai : Prompt, Publish, Play. 🌹 https://t.co/zDq6c6v7D1 🎓 Founder. PhD AI Berkeley 👼 Angel investing https://t.co/VMlOAnTC1jKrzysztof Choromanski @kchorolab
390 Followers 131 Following Mind of a scientist. Heart of a mathematician. Soul of a pianist. Research Scientist @GoogleDeepMind and Adjunct Assistant Professor @Columbia.Noah Giansiracusa @ProfNoahGian
8K Followers 5K Following As seen on @CNN. Math Prof @BentleyU. Forthcoming pop math book @riverheadbooks. Words on AI+algos+misinfo @washingtonpost @TIME @SciAm @BostonGlobe @WIREDBasil Mustafa @_basilM
1K Followers 130 Following researching ML @ google brain ZRH | no strong opinions about AI, but very strong opinions about why herbal infusions are awful and should not be called teasMatthew Johnson @SingularMattrix
12K Followers 3K Following Researcher at Google Brain. I work on JAX (https://t.co/UGa5tGfinF).Corey Lynch @coreylynch
10K Followers 1K Following AI at @figure_robot, previously research scientist at @GoogleDeepMind.Tengyu Ma @tengyuma
25K Followers 512 Following Assistant professor at Stanford; Co-founder of Voyage AI (https://t.co/wpIITHLgF0) ; Working on ML, DL, RL, LLMs, and their theory.Hossein Mobahi @TheGradient
6K Followers 691 Following Senior Research Scientist @GoogleAI. I ∈ Optimization ∩ Machine Learning. Fan of @IronMaiden🤘.Here to discuss research 🤓Greg Yang @TheGregYang
53K Followers 661 Following Cofounder https://t.co/SpHbO7FZNV. Morgan Prize Honorable Mention 2018. Developing the theory of #TensorPrograms and the practice of scaling #neuralnetworks.Hugo Larochelle @hugo_larochelle
113K Followers 625 Following Google DeepMind researcher, machine learning professor, ex-Twitter Cortex, father of 4, wine/music/comedy enthusiastNando de Freitas 🏳.. @NandoDF
97K Followers 658 Following I research intelligence to understand what we are, and to harness it wisely. I lead a wonderfully creative AI team at @GoogleDeepMind who inspire me everyday.Aleksandra Faust @AleksandraFaust
2K Followers 515 Following Research Scientist with Google @Deepmind. Previously, @GoogleAI in #GoogleBrain. @Waymo, @SandiaLabs, @UNM, @UIUC.Haydee @HaydeeLindo
2K Followers 893 Following Algebraist || Asst Prof of Math @ Harvey Mudd College || Alchemist || #NsfFunded #WOCinSTEM || 🇯🇲 || views = mine || semper vigilansLaurent Dinh @laurent_dinh
5K Followers 770 Following Internet pedestrian. ✨Content creator✨ (ML researcher). Tweets were not peer reviewed. (he/him/his). Mastodon: https://t.co/jawvygfDHArodolphe_jenatton @RJenatton
357 Followers 272 FollowingMartin Wattenberg @wattenberg
18K Followers 509 Following Human/AI interaction. Visualization as design, science, art. Professor at Harvard, and part-time at Google's People+AI Research initiative.imagine paying 44 bil.. @pwr2dppl
5K Followers 657 Following this place is dead anyway. catch me elsewhere. blocking new follows.Alex Kontorovich @AlexKontorovich
24K Followers 805 Following Mathematician (Distinguished Professor of #Math at @RutgersU). Here to learn about research, education, and community. Let’s build something together.Timothy Gowers @wtgow.. @wtgowers
44K Followers 188 Following Mathematician. Professeur titulaire de la chaire Combinatoire au Collège de France. Also fellow of Trinity College Cambridge.Jason Lee @jasondeanlee
10K Followers 3K Following Associate Professor at Princeton and Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learningElad Hazan @HazanPrinceton
11K Followers 187 Following machine learning and optimization @PrincetonCS & Google DeepMind Princeton, dad^3Ryan Williams @rrwill.. @rrwilliams
7K Followers 413 Following Professor @MITEECS and @MIT_CSAIL. I study computational complexity, algorithm design, and their math. I'll let you know when P != NPBarret Zoph @barret_zoph
10K Followers 880 Following @openai Past: Research Scientist at Google Brain.Colin Raffel @colinraffel
30K Followers 654 Following nonbayesian parameterics, sweet lessons, and random birds. Friend of @srush_nlpLei Chen @leichen1994
261 Followers 585 Following CS Ph.D. student @ NYU Courant. Previously @Tsinghua_Uni undergrad.Sanjeev Arora @prfsanjeevarora
21K Followers 32 Following Director, @PrincetonPLI and Professor @PrincetonCS. Seeks math/conceptual understanding of deep learning and large AI models.Gil Kalai @GilKalai
3K Followers 255 FollowingPeter J. Liu @peterjliu
4K Followers 2K Following Research Scientist @ Google B̵r̵a̵i̵n̵ DeepMind, frontier language models research (aka chatbot engineer). Opinions are my own. 🤖🔄🚀George E. Dahl @GeorgeEDahl
4K Followers 119 Following Machine learning researcher @Google research. My opinions do not necessarily represent my employer. Prefer email over DMs. https://t.co/FI9gvTzCbO…Many of these trends don't hold. Last week we celebrated @geoffreyhinton's retirement, and a few weeks earlier saw @kkariko receive the Nobel Prize. Their research took decades to come together, and had enormous impact at a world scale. We'd be much worse off if they'd pivoted!
Enjoyed visiting UC Berkeley’s Machine Learning Club yesterday, where I gave a talk on doing AI research. Slides: docs.google.com/presentation/d… In the past few years I’ve worked with and observed some extremely talented researchers, and these are the trends I’ve noticed: 1. When…
not only is @jmgilmer a beast at debugging large scale transformers, he can also do a graduate thesis's worth of mathematics in an hour long walk A Constant Lower Bound for Frankl's Union-Closed Sets Conjecture youtu.be/veMx-r1iQpY via @YouTube
Startling new from a seminar in Cambridge about a problem of Erdős. Which problem??? gilkalai.wordpress.com/2023/03/16/som…
The confusion of people assigning human attributes stems from the fact that humans use language to communicate their internal state quite often. LLMs never communicate their internal state. They just aim to model the distribution of past human outputs in certain contexts.
Simplest example of warm-up being useful. Minimize (x*y)^2. Gradient descent with exponentially increasing learning rate recovers least-norm solution, constant learning rate does not. Petal-shape is due to some initial points requiring more steps to converge.
@poolio Not sure what you’re after and why. There is a concept of measure and density on a manifold. In your case, the manifold is R^D and the density is the Gaussian. Apparently, there is also the concept of “fuzzy manifold” but that seems like a whole other can of worms 😅
(6/6) ...sin embargo no se ha probado que converja a algún número. Lo que sí se sabe (lo probó Justin Gilmer @jmgilmer en 2013), es que la densidad de números felices está acotada entre 0.1138 y 0.18577. degruyter.com/document/doi/1…
I love my partner to death, but dear god, I made the mistake of peeking at some simulation source code he was writing. Never look at source code written by Physicists.
You Wouldn't Last 48 Hours In The Real Wild West...
MIT CSAIL is excited to announce the Mentored Opportunity in Research Postdoctoral Fellowship (Meteor), to broaden participation in computing and artificial intelligence: csail.mit.edu/meteor
I finally found time to put my PhD thesis on arxiv. Check it out! Thanking everyone who made this thesis possible 🖤🎊 arxiv.org/abs/2104.12053
I'm struck by how the divide in the US is not between red states and blue states but between urban and rural regions. This is certainly true in Oregon. 1/
We may be opponents — but we are not enemies. We are Americans.
This 2019 paper on Fourier analysis of adversarial robustness, by Dong Yin et al., is really worth a look. It gives a simple, intuitive way of understanding a wide variety of adversarial and robustness phenomena. papers.nips.cc/paper/9483-a-f…
Check out our new paper on adversarial robustness as a prior for better transfer learning! A great colab w/ @andrew_ilyas @logan_engstrom @akapoor_av8r @aleks_madry We open-source ~70 robust ImageNet models which you might find helpful! github.com/microsoft/robu…
Does adv. robustness help transfer learning? W/ @hadisalmanX @andrew_ilyas @logan_engstrom @akapoor_av8r @MSFTResearch we show l2-robust ImageNet models transfer better, despite lower accuracy: arxiv.org/abs/2007.08489. Blog: gradientscience.org/transfer-learn… Code: github.com/microsoft/robu…
Apropos of recent discussions on whether "Lp robustness is useful", @RICEric22 and I have a new paper on learning adversarial perturbation models from data. This learns to map an L2 latent space (over which we perform adversarial training) to "realistic" perturbations of inputs.
1/ New paper on learning perturbation sets for robust machine learning! We study how to characterize real world perturbations in a well-defined set. Paper: arxiv.org/abs/2007.08450 Blog post: locuslab.github.io/2020-07-20-per… Code: github.com/locuslab/pertu… Joint work with @zicokolter
1/ New paper on learning perturbation sets for robust machine learning! We study how to characterize real world perturbations in a well-defined set. Paper: arxiv.org/abs/2007.08450 Blog post: locuslab.github.io/2020-07-20-per… Code: github.com/locuslab/pertu… Joint work with @zicokolter
@jmgilmer @tdietterich Totally agreed. Perhaps some nuance is lost in orig tweet and I should watch your talk :) I think most of community now views Lp as test for methods, rather than directly useful task (similar to e.g. CIFAR-10). IMO, Lp work still important but needs clarity on true motivation.
@quantrad I think Justin would say rather that data shift is a huge problem and that if we solve it, we will also have solved the adversarial example “problem”
@SebastienBubeck Interesting. I view adversarial examples as a symptom of a weakness (cannot write disease because this is twitter and I'd be eaten alive even though I have no bad intentions). Then the question is whether you want to treat the symptom, or discover and cure the weakness.