Mathieu Blondel @mblondel_ml
Research scientist at Google DeepMind. Current research interests: differentiable programming, LLMs, Transformers. mblondel.org Paris, France Joined June 2009-
Tweets4K
-
Followers9K
-
Following416
-
Likes2K
I think people should just go back to using linear models then…
I think people should just go back to using linear models then…
Regarding work load as an AC at ICML this year. In most cases, having 4 reviewers per paper didn't help and 14 out 15 papers in my stack had a score between 4 and 6. I think reallocating 1/4 of the reviewers to area chairing would be better, since the AC needs to make the call.
Some stats on ICML 2024 load as an AC this year. I have 17 papers in my batch. 2 have been withdrawn so I need to write 15 meta reviews. 14 out of these 15 papers have a score between 4 and 6. The review signal is very weak so I need to carefully read 15 papers and rebuttals.
We are excited to announce that the second edition of our workshop on Differentiable Almost Everything got accepted to #ICML2024 in Vienna 🎻! Check out our updated website: differentiable.xyz @CuturiMarco @HildeKuehne @Michael_A_Kagan @StefanoErmon @icmlconf
[75min talk] i finally recorded this lecture I gave two weeks ago because people kept asking me for a video so here it is, enjoy "The Little guide to building Large Language Models in 2024" tried to keep it short and comprehensive – focusing on concepts that are crucial for…
The only question reviewers should be asking themselves: "Is the community better off with this paper, or without it?" inappropriate reasons for rejection include: not beating SOTA, bad writing, minor flaws, no theory yet good results, incomplete citations (easily fixed),.....
For #InternationalWomensDay, our co-founder and principal research scientist, @ZeldaMariet, talks about how she got into tech, her advice for women who want to enter the field, and how you should always use a versioning system.
Big update to #optax! v0.2.0 is out with backtracking line-search 🚀 This means learning-rate free optimizers like Armijo SGD are now easier than ever to implement. What experiments will you try first?
Often overlooked fact: virtually all recent LLM software stacks rely on SentencePiece, a tokenization library developed by Taku Kudo at Google Japan, itself based on the BPE paper.
Often overlooked fact: virtually all recent LLM software stacks rely on SentencePiece, a tokenization library developed by Taku Kudo at Google Japan, itself based on the BPE paper.
I’m proud to announce our launch of @bioptimus_ai – with a mission to create and build the first #foundationmodel for biology. (1/3)
One of the big lessons of transformers compared to old school NLP is that it's much better to use a large context p(y_i | y_{i-1}, ..., y_{i-c}) with ancestral sampling than a small context p(y_i | y_{i-1}) with exact inference.
🚨 Paper alert: 𝗜𝗺𝗽𝗹𝗶𝗰𝗶𝘁 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻! New work on taking gradients through sampling process, e.g. in diffusion models w @PierreMari0n @Korba_Anna Peter Bartlett @mblondel @ValentinDeBort1 @ArnaudDoucet1 @FelipeLlinares @cypaquette arxiv.org/abs/2402.05468
Checkout DeRa, our simple approach for controlling the degree of alignment of an LLM at *decoding time*, by interpolating between the SFT and aligned models. We provide a mathematical justification for the approach and a thorough empirical verification.
Checkout DeRa, our simple approach for controlling the degree of alignment of an LLM at *decoding time*, by interpolating between the SFT and aligned models. We provide a mathematical justification for the approach and a thorough empirical verification.
Online feedback is crucial for alignment, so we propose a simple recipe to make any direct alignment method (think DPO / IPO / SLiC-HF) online using AI feedback 🧙♂️ In human evals, online methods yield on avg 66% wins, 28% ties and 6% losses vs offline methods (on TL;DR) 👀
Online feedback is crucial for alignment, so we propose a simple recipe to make any direct alignment method (think DPO / IPO / SLiC-HF) online using AI feedback 🧙♂️ In human evals, online methods yield on avg 66% wins, 28% ties and 6% losses vs offline methods (on TL;DR) 👀
For a small fee, I will attend your enemy’s conference talk and will stare at them awkwardly the whole time without looking at the slides a single time.
For a small fee, I will attend your enemy’s conference talk and will stare at them awkwardly the whole time without looking at the slides a single time.
I like the Mamba paper but why the heck is it already a Wikipedia article? en.wikipedia.org/wiki/Mamba_(de…
In these exciting times for mixture-of-experts (MoE) models, I am happy to share our paper “Routers in Vision Mixture of Experts: An Empirical Study” with @mblondel_ml, @rikelhood, and @joapuipe: arxiv.org/abs/2401.15969
Linus Torvalds seems to be very positive about LLMs for code youtu.be/VHHT6W-N0ak?si…
Nick Higham's blog was a gold mine nhigham.com
Nick Higham's blog was a gold mine nhigham.com
I'd like to start 2024 with some thoughts on the state of optimization theory. To begin with, let me quote Nesterov's 2003 book: "The main fact, which should be known to any person dealing with optimization models, is that, in general, the optimization problems are unsolvable" 🧵
Gabriel Peyré @gabrielpeyre
92K Followers 450 Following @CNRS researcher at @ENS_ULM. One tweet a day on computational mathematics.
Peyman Milanfar @docmilanfar
67K Followers 261 Following Distinguished Scientist at Google Research. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.
Frank Nielsen @FrnkNlsn
23K Followers 1K Following Machine Learning & AI, Information Sciences & Information Geometry, Distances & Statistical models, HPC. "Geometry defines the architecture of spaces" @SonyCSL
Lucas Beyer (bl16) @giffmana
56K Followers 445 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]
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 🌈
Dan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)
Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).
Eric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0p
Sam Power @sp_monte_carlo
17K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. (he / him)
Michael Bronstein @mmbronstein
43K Followers 4K Following #DeepMind Professor of #AI @UniofOxford / Fellow @ExeterCollegeOx / ML Lead @ProjectCETI / https://t.co/kZpGpDzYeV
Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).
rohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.
Michal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMind
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. Sustainability
yobibyte @y0b1byte
15K Followers 2K Following Kurin ViTaly, senior research scientist @IsomorphicLabs, ML PhD from @UniofOxford on RL, Multitask learning & Graphs
Pierre Alquier @PierreAlquier
8K Followers 5K Following Professor of Statistics @ESSEC_AP 🇸🇬 // Previously @RIKEN_AIP 🇯🇵 @ENSAEparis 🇫🇷 @ucddublin 🇮🇪 🇪🇺 // random posts about research & birds photos // 🌈
Pasquale Minervini �.. @PMinervini
7K Followers 4K Following Researcher in ML/NLP at the University of Edinburgh (faculty @InfAtEd @EdinburghNLP), @ELLISforEurope, @UCL_NLP, PI for @Clarify2020, https://t.co/WydvfU8ugz he/they
Gael Varoquaux @GaelV.. @GaelVaroquaux
22K Followers 318 Following Research & code: Research director @inria ►Data, Health, & Computer science ►Python coder, (co)founder of @scikit_learn & joblib ►Art on @artgael ►Physics PhD
Lénaïc Chizat @LenaicChizat
2K Followers 240 Following Assistant professor @epfl (previously @cnrs researcher). Interested by what's simple, beyond the obvious.
mestresilêncio @sunkenspirits
18 Followers 25 Following
Arif Ahmad @ArifAhm92263086
210 Followers 6K Following All things AI, Computer Science and Circuits! Prev. @GoogleAI
Ramis Cizer @RamisCizer
251 Followers 522 Following Social Psychology Postgrad, Data Engineering enthusiast. At an interval, trying to find my criticality. Atheist, burgeoning futurist.
Mark Jimenez @realmarkjimenez
33 Followers 195 Following
Arthur Cerf @ArthurCerf
897 Followers 1K Following
Pensé FFun @inftyCategory
118 Followers 5K Following
Witcher_E @Witcher_E
9 Followers 49 Following
Apostolos Tsakalos @tsakap1982
79 Followers 4K Following Deep Learning in Finance @[email protected]
Digital Cathouse @DigitalCathouse
220 Followers 208 Following #AI powered hyper-realistic #altgirl models 🔥 100% fictional, unique & original art 🎛️ No real people depicted ✌️
Avrajit Ghosh @GhoshAvrajit
197 Followers 629 Following Computational math PhD student, Michigan State University. Generalization, optimization, Inverse problems. (No prior) better than (wrong priors).
Daniel Blasko @blskdan
231 Followers 1K Following Final year MEng. in Data Science at TU Wien & Software Engineering at INSA Lyon
Maurice Kraus @mkraus_io
41 Followers 59 Following PhD student @ AIML - TU Darmstadt. Passionate about finding ways to make complex models more transparent and understandable. #timeseries #XAI #research
Dasaem Jeong @DasaemJ
588 Followers 410 Following Assistant Professor @ Dep. of Art & Technology, Sogang Univ. MIR/Deep Learning/Creative AI
Pei Liu @lipi68654341332
18 Followers 97 Following
Hossein Sharifi N. @Hossein_SHN
705 Followers 2K Following ML Researcher @BorealisAI | Ph.D. in Computer Science @SFU | Developing intelligent machines | Previously: @VanProstateCtr, @pmcancercentre, @Novartis
libertyhhn @libertyhhn
4 Followers 61 Following
Haozhe Ji @HaozJi
41 Followers 88 Following Grad student @ Tsinghua university | NLPer | I play the cello
Bo Lin @bolin0812
144 Followers 348 Following PhD candidate @UofT | OR + ML for transportation + sustainability | Formerly @UWaterloo and @Tsinghua_Uni.
Mahmoud Hegazy @oumatheu
4 Followers 75 Following
lxcell @lx_cell
23 Followers 312 Following
ChritineReneilt @CReneilt24520
17 Followers 398 Following
Donghyun Oh @DonghyunOh1
17 Followers 223 Following phd student at POSTECH. interested in ML, optimization, basketball, math etc
Arash @ArashJm
414 Followers 2K Following Interested in Computer Science & Mathematics, AI @ Sharif, INTJ
Zhiyong Wang @Zhiyong16403503
378 Followers 2K Following Visiting Ph.D. student at Cornell University. Ph.D. candidate at CUHK. Working on bandits and reinforcement learning theory.
snir hordan @HordanSnir
28 Followers 110 Following
Tonmoy Hossain @TonmoyHDihan
45 Followers 359 Following
Azerbaïdjan @Lira0032
9 Followers 46 Following
Alex Atanasov @ABAtanasov
733 Followers 1K Following Fascinated by scaling and universality. PhD Candidate @HarvardPhysics. 🇧🇬
Felipe Avila @felavila2
60 Followers 1K Following PhD student in astrophysics at @IFA_UV, working on gravitational lensing. From Cucao Chiloe.
Casa Amarilla @casaOxidada
106 Followers 216 Following
Joe Greener @jgreener64
1K Followers 776 Following Computational chemist/structural bioinformatician working on improving molecular simulation at MRC Laboratory of Molecular Biology.
Abe Chide @AbeChide
0 Followers 124 Following
Wei Shi @weishi
53 Followers 934 Following
Diego Bellani @diegobellani
24 Followers 780 Following
Xu Zu @XuBing36614469
42 Followers 198 Following
Gabriel Peyré @gabrielpeyre
92K Followers 450 Following @CNRS researcher at @ENS_ULM. One tweet a day on computational mathematics.
Peyman Milanfar @docmilanfar
67K Followers 261 Following Distinguished Scientist at Google Research. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.
Frank Nielsen @FrnkNlsn
23K Followers 1K Following Machine Learning & AI, Information Sciences & Information Geometry, Distances & Statistical models, HPC. "Geometry defines the architecture of spaces" @SonyCSL
Kevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.
Lucas Beyer (bl16) @giffmana
56K Followers 445 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]
Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).
Eric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0p
Sam Power @sp_monte_carlo
17K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. (he / him)
Michael Bronstein @mmbronstein
43K Followers 4K Following #DeepMind Professor of #AI @UniofOxford / Fellow @ExeterCollegeOx / ML Lead @ProjectCETI / https://t.co/kZpGpDzYeV
Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).
NeurIPS Conference @NeurIPSConf
111K Followers 35 Following New Orleans, Dec 10-16, 23. https://t.co/ga8aOw615g Tweets to this account are not monitored. Please send feedback to [email protected].
rohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.
Michal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMind
yobibyte @y0b1byte
15K Followers 2K Following Kurin ViTaly, senior research scientist @IsomorphicLabs, ML PhD from @UniofOxford on RL, Multitask learning & Graphs
Pierre Alquier @PierreAlquier
8K Followers 5K Following Professor of Statistics @ESSEC_AP 🇸🇬 // Previously @RIKEN_AIP 🇯🇵 @ENSAEparis 🇫🇷 @ucddublin 🇮🇪 🇪🇺 // random posts about research & birds photos // 🌈
Gael Varoquaux @GaelV.. @GaelVaroquaux
22K Followers 318 Following Research & code: Research director @inria ►Data, Health, & Computer science ►Python coder, (co)founder of @scikit_learn & joblib ►Art on @artgael ►Physics PhD
Lénaïc Chizat @LenaicChizat
2K Followers 240 Following Assistant professor @epfl (previously @cnrs researcher). Interested by what's simple, beyond the obvious.
Peter Richtarik @peter_richtarik
6K Followers 591 Following Federated Learning Guru. Tweeting since 20.5.2020. Lived in 🇸🇰🇺🇸🇧🇪🇬🇧🇸🇦
Daniel Johnson @_ddjohnson
2K Followers 571 Following Researcher at @GoogleDeepMind. PhD student at @VectorInst / @UofT. Building tools to study neural nets and find out what they know. He/him.
kyutai @kyutai_labs
6K Followers 6 Following
Haozhe Ji @HaozJi
41 Followers 88 Following Grad student @ Tsinghua university | NLPer | I play the cello
Benjamin Guedj @bguedj
3K Followers 5K Following Machine learning researcher @Inria @ucl | @ai_ucl @uclcs @Inria_Lille @turinginst Scientific director of #InriaLondon Young Leader @francobritish 🇫🇷🇪🇺🇬🇧
Julien Chaumond @julien_c
46K Followers 1K Following Co-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @Polytechnique
koray kavukcuoglu @koraykv
8K Followers 84 Following VP of Research and Technology at Google DeepMind
Amy C. Chou @AmyCChou
948 Followers 5K Following Program Manager @Google: Health AI, AI for Social Good, Impact-Driven Research, Innovation, Moonshots. @UChicago grad, cancer survivor, @UeliRutishauser's wife.
Charles Riou @CharlesRiou007
63 Followers 173 Following PhD in CS/ML at the University of Tokyo - Master MVA - Ecole Polytechnique — Maths and Tennis enthusiast
Aakanksha Chowdhery @achowdhery
7K Followers 3K Following LLMs @ Google DeepMind :: PaLM, Gemini // Previously @MSFTResearch, @Stanford, @Princeton // views my own and subject to change
Ben Grimmer @prof_grimmer
3K Followers 431 Following Assistant Professor @JohnsHopkinsAMS, Optimization, PhD @CornellORIE Mostly here to share pretty maths/3D prints, sometimes sharing my research
Felix Köhler @felix_m_koehler
1K Followers 424 Following 🤖 Machine Learning & 🌊 Simulation | 📺 YouTuber | 🧑🎓 PhD student @thuereyGroup
Marie Pellat @m_pellat
1K Followers 196 Following AI Scientist, @MistralAI - previously Google // Responsible AI
fllinares @FelipeLlinares
21 Followers 35 Following
Pierre Richemond 🇪.. @TheOneKloud
2K Followers 590 Following @GoogleDeepMind Research Scientist. Studied @ImperialCollege, Paris VI - @Polytechnique, ENST, @HECParis. Prev @GoldmanSachs.
Bioptimus @bioptimus_ai
394 Followers 2 Following We build foundation models that will transform biology.
Ibrahim Alabdulmohsin.. @ibomohsin
906 Followers 582 Following AI Research Scientist at @GoogleDeepmind
Thomas Mesnard @Mesnard_Thomas
417 Followers 290 Following Research Scientist @GoogleDeepMind since 2019. Working on LLM: pretrain, IT, RLHF, RLAIF. PhD @IP_Paris_ | @Mila_Quebec | MSc MVA @ENS_ParisSaclay | @ENS_ULM
Zelda Mariet @ZeldaMariet
504 Followers 659 Following The fire fades, and the lords go without thrones.
Shangmin Guo @ShawnGuo13
113 Followers 131 Following PhD student@Uni of Edinburgh, curious about how humans and AI co-exist and co-evolve
Neil Houlsby @neilhoulsby
4K Followers 317 Following Professional AI researcher; amateur athlete. Senior Staff RS in the Google Deepmind, Zürich. Attempts triathlons.
Alexandre Ramé @ramealexandre
1K Followers 659 Following Research scientist @GoogleDeepMind. Ph.D. @Sorbonne_Univ_. Averaging weights to align AIs.
Sarah Perrin @sarah_perrin_
491 Followers 436 Following Research Scientist @GoogleDeepMind. Reinforcement Learning, Mean Field Games & Game theory
Charlotte Caucheteux @c_caucheteux
2K Followers 260 Following Research Scientist @MetaAI | Deep Learning | Large Language Modelling | Cognitive Neuroscience
Gintare Karolina Dziu.. @gkdziugaite
4K Followers 107 Following Sr Research Scientist at Google DeepMind, Toronto. Member, Mila. Adjunct, McGill CS. PhD Machine Learning & MASt Applied Math (Cambridge), BSc Math (Warwick).
Miloš Stanojević @milosstanojevic
637 Followers 603 Following Research scientist @DeepMind • Natural language processing • Parsing • Formal Languages • https://t.co/NBa754qVmY
Vincent Roulet @vincentrouletx
39 Followers 2 Following
Laurent Daudet @Laurent_Daudet
1K Followers 1K Following CoCEO at https://t.co/7tBdXi7xiV building foundation AI models. Prof @univ_paris_cite on leave. Co-author of Dream Machine graphic novel on AI. PP by @WorldOfHalahala
Ronny Bergmann (sehr .. @ronnybergmann_
503 Followers 166 Following Tweeting about research in optimisation & variational methods on manifolds, and numerics in Julia (Manifolds.jl & Manopt.jl). Working @ntnuNorway.
Jia-Jie Zhu @__jzhu__
603 Followers 204 Following Head of research group in optimization / machine learning @WeierstrassInst Berlin. Former postdoc in machine learning @MPI_IS Tübingen, PhD in optimization @UF.
Ramith Hettiarachchi @ramith__
888 Followers 4K Following Visiting Scientist @MIT, Post-Bac Fellow @Harvard Interested in ML for science while striving for trustworthiness Ex: @ENTC_UOM 🇱🇰 @CSIRO 🇦🇺 @RotaractMora
Emile van Krieken @EmilevanKrieken
2K Followers 1K Following Postdoc @ University of Edinburgh | Neurosymbolic Machine Learning
Ehsan Amid @esiamid
725 Followers 226 Following Senior Research Scientist @GoogleDeepMind 🌱🧠🌼🐝 (opinions my own just in case)
Mahesh Sathiamoorthy @madiator
9K Followers 929 Following LLMs and Data. Discuss about data for LLMs: https://t.co/x4iAft5cHV Ex-GoogleDeepMind
James Morrison Rubin @import_jmr
6K Followers 6K Following Product Lead | Bringing Gemini to life @Google Tweets are my own. Retweets are not endorsements. Joyful Learning Machines
Hanjun Dai @hanjundai
1K Followers 271 Following Research Scientist at Google DeepMind; https://t.co/iRgaYGVC2U
Eric Chu @its_ericchu
2K Followers 791 Following Research scientist @ Google DeepMind. AI reasoning + alignment/safety to help humans. Gemini, Bard, PaLM 2. Prev PhD @ MIT.
Marin Vlastelica 🤖.. @vlastelicap
1K Followers 1K Following Final year PhD @ Max Planck Institute for Intelligent Systems 🤖 | All things ML 🎲 | ex. @DeepMind, @amazon 🇭🇷🇩🇪🎸🏀🎾
Thomas Möllenhoff @tmoellenhoff
649 Followers 463 Following Research Scientist (tenured) @RIKEN_AIP @RIKEN_EN — PhD from @TU_Muenchen @tumcvg
Laurent Sifre @laurentsifre
1K Followers 411 Following Research Scientist @DeepMind since 2014. Worked on #AlphaGo #AlphaFold and #AlphaStar, now focused on #NLP at scale.
Aart Bik @AartBik
1K Followers 800 Following 🇳🇱🇺🇲 Dutch-American computer scientist Utrecht (MSc), Leiden (PhD) @Google @Intel #MLIR #LLVM #astronomy #chess #compilers #simd #sparse #vectorization
Flavien Prost @FlavienProst
108 Followers 124 Following @Google researcher, working on ML Fairness and Recommender Systems
Pierre Colombo @PierreColombo6
451 Followers 1K Following Associate Professor at Université Paris Saclay - CentraleSupelec - NLP - GenAI
Jascha Sohl-Dickstein @jaschasd
19K Followers 622 Following Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.
Felix Petersen @FHKPetersen
1K Followers 194 Following Machine learning researcher, postdoc, 24 y/o. Investigating differentiable algorithms etc. @Stanford @StanfordAILab.
Hilde Kuehne @HildeKuehne
3K Followers 764 Following Professor for CS at @UniBonn and affiliated Professor at MIT-IBM Watson AI lab @MITIBMLab - Multimodal learning and video understanding
Pauline Luc @paulineluc_
464 Followers 500 Following Research Scientist @Deepmind - 🦩 | ex PHD at @MetaAI & @Inria
Charlotte Bunne @_bunnech
3K Followers 485 Following PostDoc at @Genentech and @Stanford and Incoming Assistant Professor at @EPFL in Computer Science and Life Sciences.product managers in eng meetings
To all the defeatists who think there is nothing else but scale: * 5 years between Self-Attention Is All You Need and FlashAttention * Transformers still require warmup. Researchers: get back to work! The future is bright :)
Made this when I was bored and I don't care to refine it more so here you go - visualizing how the frank-wolfe algorithm works on a simple example: the constraint set is an octagon in R^2 and the objective function is just the squared distance to the point a (denoted by a star).
Couldn't make it to Seoul for ICASSP but thanks for the recognition @IEEEsps !
RNNs *are* state-space models. This seems more like linear vs non-linear SSM distinction.
✨Excited to finally drop our new paper: SSMs “look like” RNNs, but we show their statefulness is an illusion🪄🐇 Current SSMs cannot express basic state tracking, but a minimal change fixes this! 👀 w/ @jowenpetty, @Ashish_S_AI arxiv.org/abs/2404.08819
@mblondel_ml Alternatively, one could ask reviewers to only use 4 scores: strong reject, reject, accept, strong accept
@mblondel_ml I feel you @mblondel_ml … had 20 papers in my stack, 2 withdrawn, 2 had average of 7 and 3 were below 5. The remaining 13… well, let’s say that kept me busy during my Easter holidays (sic). I’m this close to reporting reviewers than only use 5 and 6.
some 3D artist learned so much about tongues working on this
Animal tongue comparison
🚀Exciting news! Our Python package, skglm, is pushing back the limits of sklearn Last week two industrial feedbacks revealed that it solves problems in seconds that sklearn struggled with for hours So happy to see our academic work have such impact! github.com/scikit-learn-c…
The NYTimes disappoints again. :-(
We are excited to announce that the second edition of our workshop on Differentiable Almost Everything got accepted to #ICML2024 in Vienna 🎻! Check out our updated website: differentiable.xyz @CuturiMarco @HildeKuehne @Michael_A_Kagan @StefanoErmon @icmlconf
@Mat_Dag @vaiter @tomamoral @iclr_conf Also worth pointing out is this brand new reference by @mblondel_ml and @vincentrouletx with a nice chapter about second-order auto diff arxiv.org/abs/2403.14606
@mblondel_ml @PierreAblin Right, so I think (regularized) Newton method is great mostly when we have a very fast linear system solver, either using CG, which needs a finite number of iterations, or by matrix decomposition. But this is probably only relevant in smallish dimensions.
I am thrilled to announce that I have been promoted to the position of full Professor at the University of Tokyo. I am immensely grateful to everyone who has supported me along the way!
During my PhD, my advisor would tell me “never use a symbol in text without reminding what it is.” [Example] 𝘉𝘢𝘥: “So, 𝜑 is bounded.” 𝘎𝘰𝘰𝘥: “So, the value function 𝜑 is bounded.”
I told a grad-student co-author "try to imagine me as the guy from 'Memento' who can't remember anything & needs clues to pick-up the thread on projects" and they said "I believe you, because you already used that memento analogy"
But then again, wasn't *every* insight tweeted by @gabrielpeyre at some point?
Indeed! A much needed book.
This looks cool: Mathieu Blondel (@mblondel_ml) and Vincent Roulet have posted a first draft of their book on arXiv: arxiv.org/abs/2403.14606
Trends for United States
You might like
