Khue Le @netw0rkf10w
Head of R&D at https://t.co/8xAGSIErb7. Building conversational AI by day, doing optimization research by night. khue.fr Paris, France Joined September 2010-
Tweets519
-
Followers293
-
Following135
-
Likes242
🥁 Llama3 is out 🥁 8B and 70B models available today. 8k context length. Trained with 15 trillion tokens on a custom-built 24k GPU cluster. Great performance on various benchmarks, with Llam3-8B doing better than Llama2-70B in some cases. More versions are coming over the next…
While waiting for @aaron_defazio's tuning result, here's my full run of his method (green curve). Interestingly, some modifications inspired by my optimizer seem to boost its performance. Note: MAE's default hyper-params are used for all experiments.
While waiting for @aaron_defazio's tuning result, here's my full run of his method (green curve). Interestingly, some modifications inspired by my optimizer seem to boost its performance. Note: MAE's default hyper-params are used for all experiments. https://t.co/c291w4Ydtb
Hi @aaron_defazio. Here's the result of my optimizer, compared to yours (still running). Can you beat my blue curve with hyper-parameter tuning? ;) Please give it a try using this code: github.com/facebookresear…
Hi @aaron_defazio. Here's the result of my optimizer, compared to yours (still running). Can you beat my blue curve with hyper-parameter tuning? ;) Please give it a try using this code: github.com/facebookresear… https://t.co/daVV01erdA
Summary of the rookie mistakes made by the Keras team:
New blog post: Yet Another ICML Award Fiasco The story of the @icmlconf 2023 Outstanding Paper Award to the D-Adaptation paper with worse results that the ones from 9 years ago Please share it to start a needed conversation on mistakenly granted awards parameterfree.com/2023/08/30/yet…
Elle est géniale cette pub d’Orange ! (bon 3 millions de vues je suis sûrement le dernier à la découvrir) youtu.be/D_HPiaAx_QA
Interesting ideas of using Optimal Transport for learning to align two sequences of features.
Interesting ideas of using Optimal Transport for learning to align two sequences of features.
Fantastic work! Congrats @TimDarcet and colleagues!
Fantastic work! Congrats @TimDarcet and colleagues!
[DISTINCTION 🏆] Toutes nos félicitations à @julienmairal de l'équipe-projet Thoth du centre @Inria de l'Université Grenoble Alpes, lauréat d'une bourse @ERC_Research Consolidator Grant 👏 Découvrez-en ➕ ici : inria.fr/fr/julien-mair… #MachineLearning #Algorithm
I’ve been working with @AdeptAILabs and we’ve made FlashAttention even faster for long sequences! For seqlen 8K, FlashAttention is now up to 2.7x faster than a standard PyTorch implementation even at small batch, making it easier to train better LMs with longer context 1/7
I’ve been working with @AdeptAILabs and we’ve made FlashAttention even faster for long sequences! For seqlen 8K, FlashAttention is now up to 2.7x faster than a standard PyTorch implementation even at small batch, making it easier to train better LMs with longer context 1/7 https://t.co/KI6XRLGlW2
FYI the so-called AdaGrad norm stepsize was proposed for the first time in arxiv.org/abs/1002.4862 (see theorem 2) I have seen several papers and talks at #NeurIPS22 citing the wrong work
We're releasing an optimized implementation of GPT2/GPT3 with FlashAttention🚀! This trains 3-5x faster than the Huggingface version, reaching up to 189 TFLOPs/sec per A100, 60.6% (model) FLOPs util of the theoretical maximum. 1/6 github.com/HazyResearch/f…
An ICLR 2023 submission has been accused of being a rehash of previous work, claim supported by detailed technical arguments. If true then there must be consequences. Intentional misleading contributions should not be tolerated in academic research. openreview.net/forum?id=CQsmM…
an interesting account (from www-users.cse.umn.edu/~bobko001/prep…, links to .pdf)
In our NeurIPS 2021 paper (with @inthebrownbag) we showed that CCCP is Frank-Wolfe in disguise. Happy to see other people recently rediscovering this fact and presenting it as a striking result. Want to know another equally striking fact? Mean Field is also Frank-Wolfe!👇
In our NeurIPS 2021 paper (with @inthebrownbag) we showed that CCCP is Frank-Wolfe in disguise. Happy to see other people recently rediscovering this fact and presenting it as a striking result. Want to know another equally striking fact? Mean Field is also Frank-Wolfe!👇
Still two days before the deadline for submitting @CVPR proposals! cvpr2022.thecvf.com/tutorials-call…
Congratulations to Dr. Mathilde Caron @mcaron31, who successfully defended her PhD **in person** after a brilliant presentation. The committee was prestigious with @CordeliaSchmid, Andrew Zisserman, Alyosha Efros, @dlarlus, and Alexey Dosovitskiy.
Remember when ML was a hugely important area w/far-reaching implications in literally every field, and then an ML conference ever-so-slightly changed its name to avoid alienating 50% of ppl, which caused the ML community to collapse & the field to die out? Yeah, neither do I.
AudioCodes @AudioCodes
7K Followers 2K Following A leading vendor of advanced voice networking and media solutions for the digital workplace, offering a range of innovative products, solutions and services.
ChartBreakouts🇺�... @Efalhor45351
28 Followers 2K Following 15-30% Monthly | 2 High-Conviction Stocks.Short-Term Gains: 15-20% in Days/Weeks.DM "JOIN" for WhatsApp Alerts. Live Trade Signals • Market Analysis
Nisough @Nisough184mU
20 Followers 1K Following
Armand O'Conner @conner_arm39905
13 Followers 685 Following
David @IADaavo
0 Followers 50 Following
Antonio @cadretenews
0 Followers 86 Following
Smartith @SmartithUVdfFj
62 Followers 4K Following
Sloother @SlootherQF9D3w
57 Followers 4K Following
AmeliaBecky @10fo1aqerTv52
28 Followers 3K Following
Phan Nguyễn Hữu P... @PhanP92071
0 Followers 1 Following
Arthur ARPIN @ArthurArpin
1 Followers 131 Following
Rohan Panda @RohanPanda5
1 Followers 43 Following
Mattivc @Mattivc
205 Followers 1K Following
Alyssa, Yi CHENG @YiCheng77783310
165 Followers 221 Following Ph.D. student, working on NLP for social good and conversational AI.
~ @humancompressed
133 Followers 1K Following
Sam Davis @samgd
139 Followers 600 Following
Evan Walters @evaninwords
609 Followers 539 Following ML/RL enthusiast, second-order optimization, plasticity, environmentalist. JAX is easy. @LeonardoAi_ / @canva prev 🖍 @craiyonAI
Gabriele @GaPisciotta
200 Followers 773 Following
HessianFree @HessianFree
2K Followers 2K Following something new -- dm me your resume. prev: @AIatMeta, @Caltech, @UCLA @NASAJPL PSGD
Robert Biehl @robeffect
84 Followers 180 Following Efficient and fast Computer vision for mobile and AR, love all things space. I have approximate knowledge of many things.
Thaddée Tyl @espadrine
537 Followers 450 Following Self-replicating organisms. https://t.co/f8LHXroHMG, Captain Train, Qonto. They. @[email protected]
wanlin zhu @neuromanifold
30 Followers 4K Following
Marianne Stecklina @MStecklina
100 Followers 149 Following Deep Learning Engineer @omniusHQ | @[email protected]
Vicky @GVigneshKannan
189 Followers 5K Following Life is Beautiful. :) |Storyteller/Amateur Writer|ML/DL|He/Him P.S. If you feel blue and you would like to talk to someone, feel free to DM, I will be there!
青龍聖者 @bdsqlsz
10K Followers 715 Following CPP:@pika_labs @SkyReels BusinessCooperation [email protected] [email protected] Architectural Model↓ [email protected] https://t.co/aGSCaF4wt4
Mike cc @Mcc_v_
1 Followers 97 Following
connor amorin @AmorinConnor
1 Followers 63 Following
Ahmed Anis @ahmedanis03
59 Followers 250 Following
Miguel @Miguelag24899
32 Followers 307 Following
Mikhail Grankin @mgrankin
233 Followers 354 Following The human right is to become an immortal all-mighty god.
Keo lythenghuy @huynguyrnn
0 Followers 1K Following
sakshumsharma @sakshumsharma
5 Followers 139 Following
Weinzaepfel Philippe @WeinzaepfelP
549 Followers 602 Following Research Scientist in Computer Vision at @NaverLabsEurope https://t.co/50waTh85if
Antonio Miguel @amiguelartiaga
34 Followers 283 Following
Phong Nguyen-Ha @PhongStormVN
762 Followers 1K Following Senior Research Scientist at Qualcomm, ex-intern @ Meta | Nvidia
Hao Phung @tienhaophung
174 Followers 582 Following PhD student @Cornell; former AI Research Resident @VinAI_Research; working on generative modeling & diffusion model.
JH @_JH_2k
64 Followers 156 Following
anjin_sama @Sillychap101
217 Followers 7K Following GPU-lover | Agentic AI RL Enjoyer Looking for AI/Backend Eng. roles
Fatih Dinc @fatihdin4en
3K Followers 1K Following Theoretical neuroscience + explainable AI. @KITP_UCSB and @geometric_intel postdoc. PhD in Applied Physics @stanford.
Mistral AI @MistralAI
156K Followers 0 Following Frontier AI in your hands. https://t.co/VdyEwpQsiy Apps: https://t.co/1vZA5XdBYo https://t.co/rj5G4u5sHu
kyutai @kyutai_labs
24K Followers 11 Following
Donald J. Trump @realDonaldTrump
108.8M Followers 53 Following 45th & 47th President of the United States of America🇺🇸
Elon Musk @elonmusk
225.3M Followers 1K Following
ElevenLabs @elevenlabsio
138K Followers 11 Following Our mission is to make content universally accessible in any language and voice.
OpenAI Developers @OpenAIDevs
222K Followers 1 Following Updates for developers building with the OpenAI Platform and API • Service status: https://t.co/kZwnwdYqOS • Support: https://t.co/qCi6M5ESZU
miru @miru_why
1K Followers 1K Following 3e-4x engineer, unswizzled wagmi. specialization is for warps
Vaibhav (VB) Srivasta... @reach_vb
33K Followers 361 Following chief get-shit-done officer @huggingface | F1 fan | Here for @at_sofdog’s wisdom | *opinions my own
Dylan Patel @dylan522p
94K Followers 941 Following SemiAnalysis Boutique AI & Semiconductor Research and Consulting DMs are open for consulting, quotes, or to talk shop
VCs Congratulating Th... @VCBrags
273K Followers 4K Following They're adding value™ And they're very proud of it. @BragsVentures
Ben Thompson @benthompson
255K Followers 2K Following Author/Founder of @stratechery. Host of @ditheringfm @sharptechpod. @notechben for sports. @monkbent on other networks. Home on the Internet.
Travis Jamison @Travis_Jamison
9K Followers 531 Following SMB investing platform: https://t.co/y8NQJmdauH Investing newsletter: https://t.co/aqJtyX73Vn Community: https://t.co/HxnktkbGGk SEO & GEO: https://t.co/l8fJ2axoAd
Ben Carlson @awealthofcs
288K Followers 737 Following Trying to bring some common sense to the world of finance. Book: https://t.co/c53AckMaZF Podcast: https://t.co/GrhZZzIjLv
10-K Diver @10kdiver
283K Followers 157 Following I help people understand the fundamentals of finance and investing.
Bùi Thanh Hiếu @nguoibuon_gio
43K Followers 1 Following Người Buôn Gió - Yêu quê hương Việt Nam, thích uống trà mạn
Zachary Nado @zacharynado
13K Followers 753 Following Research eng @GoogleDeepMind on Gemini pretrain. Personal acct. Past: swe intern @SpaceX, ugrad researcher in @tserre lab @BrownUniversity. All opinions my own.
Frank Schneider @frankstefansch1
693 Followers 650 Following Postdoctoral researcher at the University of Tübingen working on (benchmarking) training methods for deep learning
Aaron Defazio @aaron_defazio
8K Followers 584 Following Research Scientist at Meta Superintelligence Labs working on optimization algorithms. Fundamental AI Research (FAIR) team
Daniel Han @danielhanchen
28K Followers 2K Following Building @UnslothAI. Finetune train LLMs faster. LLMs bug hunter. OSS package https://t.co/aRyAAgKOR7. YC S24. Prev ML at NVIDIA. Hyperlearn used by NASA.
Alexis Conneau @alex_conneau
35K Followers 189 Following Co-founder and CEO https://t.co/efv72CKpAG (@WaveFormsAI) - Ex @OpenAI GPT-4o/AVM Audio Research Lead - #Her #TARS - Ex @AIatMeta, @Polytechnique (X11)
Ben Grimmer @prof_grimmer
3K Followers 433 Following Assistant Professor @JohnsHopkinsAMS, Optimization, PhD @Cornell_ORIE Mostly here to share pretty maths/3D prints, sometimes sharing my research
TimDarcet @TimDarcet
4K Followers 755 Following PhD student, building big vision models @ INRIA & FAIR (Meta)
Shashank Prasanna @shshnkp
1K Followers 188 Following AI/ML Evangelist (@apple) on-device ML, MLX, FMs. I talk/write/teach/build ML. Recreational runner🏃♂️. Passionate about AI. Math. Physics. My own opinions ↓
Académie des science... @AcadSciences
23K Followers 407 Following 🏅Soutenir la recherche 👩🔬Transmettre les connaissances scientifiques 💡 Conseiller les pouvoirs publics
MT Group at FBK @fbk_mt
1K Followers 443 Following #MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai
Lucas Beyer (bl16) @giffmana
108K Followers 519 Following Researcher (now: Meta. ex: OpenAI, DeepMind, Brain, RWTH Aachen), Gamer, Hacker, Belgian. Anon feedback: https://t.co/xe2XUqkKit ✗DMs → email
Michaël Benesty @pommedeterre33
3K Followers 665 Following Apply mathemagic to law understanding Head of R&D @LefebvreSarrut ex tax lawyer @Deloitte, CPA, financial audit, former core dev @XGBoostProject
Simon Pepin Lehalleur @plain_simon
4K Followers 6K Following Mathematician (algebraic geometry, motives & friends, singularities in statistics and ML). 'Geometry is successful magic' (R. Thom) University of Amsterdam.
Patrick Kidger @PatrickKidger
11K Followers 213 Following I do SciML + open source! 🧪ML+proteins@ https://t.co/04dWAWzCyl 📚Neural ODEs: https://t.co/ODOKWjub5k 🤖JAX ecosystem: https://t.co/8kXzaG9XVf 🧑💻Prev. Google, Oxford
Horace He @cHHillee
39K Followers 535 Following @thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale
Edward Z. Yang @ezyang
14K Followers 1K Following I work on PyTorch at Meta. Chatty alt at @difficultyang.
Tri Dao @tri_dao
32K Followers 632 Following Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.
Analysis Fact @AnalysisFact
133K Followers 19 Following Daily tweets about real and complex analysis and related topics. From @JohnDCook.
Peter Richtarik @peter_richtarik
8K Followers 649 Following Federated Learning Guru. Tweeting since 20.5.2020. Lived in 🇸🇰🇺🇸🇧🇪🇬🇧🇸🇦
Francesco Orabona @bremen79
8K Followers 411 Following Dad and associate professor at @KAUST_News. Formerly @BU_ece, @sbucompsc, @YahooResearch, @TTIC_Connect. ML theory&practice, obsessed with history of science
Tony S.F. @tonysilveti
633 Followers 347 Following Ass. Prof. (maître de conférences) of artificial intelligence at @CentraleSupelec in the Centre pour la Vision Numérique. Vélotaffeur 🇲🇽/🇺🇸
Sam Power @sp_monte_carlo
19K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. @OnlineMCSeminar. (he / him)
Not Even Wrong @notevenwrong
4K Followers 0 Following
lieven le bruyn @lievenlb
594 Followers 70 Following Grandpa (Gust/Mil), caretaker of an old house and surrounding chataigneraie (07260), retired mathematician (AG/RT), ex-blogger (neverendingbooks).
Masha Vladimirova @iamvladimirova
306 Followers 150 Following Senior Researcher @ Criteo | Fairness, Causality, Deep learning theory
Thanh Nguyen-Tang @thanhnguyentang
493 Followers 1K Following (machine) learner @JohnsHopkins; slow science; life is beautiful.
Konstantin Mishchenko @konstmish
7K Followers 652 Following Research Scientist @AIatMeta Previously Researcher @ Samsung AI Outstanding Paper Award @icmlconf 2023 Action Editor @TmlrOrg I tweet about ML papers and math
Juliette Bruce @JulietteBruce12
3K Followers 82 Following math postdoc | running | climbing | slowly going up hills
OptimaLab @optimalab1
1K Followers 234 Following Optimization for ML at Rice University (CS) led by Associate Prof. Anastasios Kyrillidis - Efficient training methods, non-convex optimization, and more.
Gautier Marti @GautierMarti1
2K Followers 852 Following #AI #Quant #MachineLearning #DeepLearning #NLP #QuantitativeTrading #StatArb #ADML #HKML #trailrunningTrends for United States
You might like
