Benoît Sagot @bensagot
Joined January 2012-
Tweets124
-
Followers614
-
Following185
-
Likes153
🤏 Why do small Language Models underperform? We prove empirically and theoretically that the LM head on top of language models can limit performance through the softmax bottleneck phenomenon, especially when the hidden dimension <1000. 📄Paper: arxiv.org/pdf/2404.07647… (1/10)
[#Parution] Benoît Sagot, “Apprendre les #langues aux machines”, @EditionsCdF, coll. “Leçons inaugurales”, en librairie à partir d’aujourd’hui college-de-france.fr/fr/editions/le… @lcdpu @cdf1530 @bensagot #apprentissage #IA #chatGPT #informatique
[À paraître] Benoît Sagot, “Apprendre les #langues aux machines”, @EditionsCdF, coll. “Leçons inaugurales”, en librairie à partir du 11 avril college-de-france.fr/fr/actualites/… @lcdpu @cdf1530 @bensagot #apprentissage #IA #chatGPT #informatique
🤩📄 We are delighted that 8 papers from the team have been accepted at @LrecColing 2024! Have a read through the titles and camera-ready versions here (in no particular order):
We're excited for the final seminar in the Collège de France series as part of @bensagot’s annual chair: 9/2/24 at 11am CET: Yann Le Cun, "L'IA axée sur les objectifs : vers des machines capables d'apprendre, de raisonner et de planifier" @ylecun @cdf1530 @AIatMeta @nyuniversity
Next seminar in the Collège de France series (as part of @bensagot’s annual chair position): 26/01/24 at 11am CET: Elena Cabrio on "Analyse automatique de l'argumentation dans les débats politiques" @ECabrio @cdf1530 @Univ_CotedAzur @inria_sophia @Laboratoire_I3S @wimmics
We are excited to announce the next seminar in the Collège de France series (as part of @bensagot’s annual chair position): 19/01/24 at 11am CET: @ClaireGardent on "Génération de texte à partir de connaissances" @cdf1530 @CNRS @synalp_nancy @labo_Loria @Univ_Lorraine
Really excited to announce that our Headless Language Models paper has been accepted at #ICLR2024 ! See you in Vienna 🇦🇹 Paper link: arxiv.org/pdf/2309.08351… @InriaParisNLP @bensagot @DeVillemonte
Really excited to announce that our Headless Language Models paper has been accepted at #ICLR2024 ! See you in Vienna 🇦🇹 Paper link: arxiv.org/pdf/2309.08351… @InriaParisNLP @bensagot @DeVillemonte
We are thrilled to announce the 2nd seminar in the Collège de France series (as part of @bensagot’s annual chair position): 15/12/23 at 11am CET: Guillaume Jacques (@rgyalrong) on “Deux exemples d’usage des transducteurs en linguistique”. @cdf1530 @CNRS @EPHE_PSL
#Science #IA "Apprendre les langues aux machines" 🖥️ La vidéo de la leçon inaugurale de Benoît Sagot (@bensagot), professeur invité sur la chaire annuelle #Informatique et sciences numériques, est disponible. 👉 college-de-france.fr/fr/agenda/leco… En partenariat avec @Inria.
Djamé.. @zehavoc
6K Followers 3K Following Associate professor in NLP, engaged citizen. Tweeting about work, life and stuffs that I care about. All my tweets can be used freely. Personal account.Inria Paris NLP (ALMA.. @InriaParisNLP
2K Followers 218 Following Twitter account of ALMAnaCH, the Inria Paris NLP research team. @[email protected]Grzegorz Chrupała �.. @gchrupala
6K Followers 1K Following Associate Professor at Tilburg University Computational Linguistics • Machine LearningAntonis Anastasopoulo.. @anas_ant
3K Followers 2K Following Assist. Prof at George Mason CS #nlproc MT, ASR, and documentation of endangered languages.Thomas Wolf @Thom_Wolf
68K Followers 4K Following Co-founder and CSO @HuggingFace - open-source and open-scienceBenjamin Muller @ben_mlr
812 Followers 2K Following Research in AI. Focusing on scaling models to the largest number of languages. Postdoc at FAIR @metaai.Pedro Ortiz Suarez @pjox13
634 Followers 791 Following Senior Research Scientist at the Common Crawl Foundation. Weird coffee person ☕️, runner 🏃🏻♂️. (he/him) 🇫🇷🇪🇺🇨🇴Leshem Choshen 🤖�.. @LChoshen
4K Followers 550 Following 🥇 Collaborative LLMs 🥈 Opinionatedly sharing #ML & #NLP 🥉 Propagating us underdogs we owe science an alternative hype @IBMResearch & @MIT_CSAILRachel Bawden @RABawden
652 Followers 208 Following Researcher in NLP in the ALMAnaCH project-team at Inria ParisKat Vylomova (कत�.. @ivrik
1K Followers 1K Following Lecturer @cis_unimelb SIGTYP @sig_typ SIGMORPHON Cyberpunk;neuro*;math for kids;fractals;C++;awk/sed/xargs/egrep; G-D-Em-C G-D-C-G Dr 🐱 Mum Views are my ownGabriele Sarti @gsarti_
2K Followers 2K Following PhD Student @GroNLP 🐮, core dev of @InseqLib (https://t.co/tTjrg26ygQ). Interpretability ∩ HCI ∩ #NLProc. Prev: @AmazonScience, @Aindo_AI, @ItaliaNLP_Lab.Christine Genin @cgenin
4K Followers 5K Following lignes de fuite : https://t.co/xGLIvR0b5f https://t.co/78O7xmZQZu https://t.co/RgT7Th5S74 https://t.co/SjnqFWCV4hSylvie Colombani @ColombaniSylvie
175 Followers 248 Following Rangeuse de livres, dompteuse d’agenda, éleveuse de shadocks, et couteau suisse. Ici on parle surtout neurodiversité, et parfois bibliothèque.Gabriel Coutagne @gabrielcoutagne
2K Followers 1K Following Intello normcore / Maître des outils (ie "redchef adjoint") @lemondefr / Prof @sciencespoEDJ / Colleur d'affiches @festjournalismeAnaïs Moutot @AnaisMoutot
5K Followers 5K Following Journaliste @LesEchosWeekEnd / ex-correspondante à San Francisco (2016-2020) / [email protected]LivingstoneWu @livingstone_wu
2 Followers 22 FollowingGeorges Le Bellier @_lebellig
177 Followers 412 Following Ph.D. student @LeCnam on domain adaptation and self-supervised learning for remote sensing 🛰 Previously intern @SonyCSL, @Ircam, @InriaEva Louise Marie Gabr.. @e681554349
9 Followers 3K Following𑀅𑀓𑁆𑀱 🌉.. @4ksh4tr4
5K Followers 5K Following Asian-African | 🦤 Zilwa | Bihārī diaspora || Anarchist | Anti-capitalist | Anti-fascist | Anti-tankie || الشعب يريد إسقاط النظام || 🏳️🌈 | NB || they/themSeán Ó hÉigeartaig.. @S_OhEigeartaigh
2K Followers 1K Following Director of https://t.co/gCEDoKdKBT at Uni of Cambridge | Researching Big Risks, and impacts of AI & emerging tech. Opinions ownShital Shah @sytelus
10K Followers 8K Following Deep learning research and code. If universe is an optimizer, what is the loss function? All opinions are my own.Andrei Mircea @mirandrom
53 Followers 301 Following PhD student @Mila_Quebec ⊗ mechanistic interpretability + systematic generalization + LLMs for science ⊗ https://t.co/xg8aE8CoWvJC Bolot @JCFLBL
32 Followers 323 Followingfrédérik coquelet @frdrikcoquelet1
2 Followers 124 FollowingNédey Oriane @NedeyOriane
6 Followers 75 FollowingSarah Bénière @sarahbeniere
35 Followers 97 Following R&D Engineer at @Inria (ALMAnaCH team) | former TNAH (prom. 2023, @Ecoledeschartes) and ECMA (2021, @LermaAmu) | interested in DH, stylistics and open scienceDenis Teyssou @dteyssou
4K Followers 6K Following Geek journalist @AFP Medialab @veraai_eu #innovation manager @InVID_EU @WeVerify verification plugin founder/maker #mediastudies #disinformation #designthinkingMathias Vast @MathiasVast1
20 Followers 123 FollowingIsmail Badache ★ @Ismail_badache
547 Followers 1K Following Associate Professor of Com💻ter Science. Information Retrieval • Social Networks • NLP • Digital Education — Latest work: https://t.co/I4RwepjBDH and https://t.co/uVzHGipq8bHanane Djeddal @HananeDjeddal
32 Followers 140 FollowingSylvain Combettes @sylvaincom
116 Followers 713 Following • Postdoctoral researcher in ML @CentreBorelli, @ENS_ParisSaclay • PhD from @ENS_ParisSaclay • Symbolic representations of time seriesBiswesh Mohapatra @bis1602
110 Followers 200 Following Multimodal Dialog Systems | PhD Student @Inria | Previously student of @IIITB_official | Interned @IBMResearch, @Siemens | GSOC 2018Laure Soulier @LaureSoulier
915 Followers 503 Following Associate professor Sorbonne University Information retrieval, NLP, Deep Learning Team @mlia_isir - Sorbonne universitéJose G Moreno @jgmorenof
323 Followers 711 FollowingJesus Lovon @jeslev4
43 Followers 407 Following Computer Science PhD student @ Université Paul Sabatierflying @FlyingKid16
10 Followers 601 FollowingSeth Aycock @sethjsa
75 Followers 542 Following NLP PhD student in Low-resource Translation at @UvA_Amsterdam Prev @InriaParisNLP.guilty/le A/bino @AubinBegue
231 Followers 2K FollowingCarolina Wardlaw @CaroliWardla
62 Followers 5K FollowingGenevieve Micks @mi_genevi
56 Followers 5K FollowingChérifa Boukacem-Zeg.. @BoukacemZeg
1K Followers 1K Following Pr. en SIC @UnivLyon1, Chargée de mission ScienceOuverte Resp @EisoImst, Open Science, Schol. Communication, Bibliometrics, Predatory Publishing, Meta-ResearchNoor Ligons @ligo_noo
30 Followers 5K FollowingCaesar @KaisaLuo
912 Followers 3K Following 𝕸𝖊𝖎𝖓 𝕳𝖊𝖗𝖟 𝖘𝖈𝖍𝖑𝖆̈𝖌𝖙 𝖗𝖊𝖈𝖍𝖙𝖘. Je ne suis pas d'accord avec ce que vous dites mais je me battrait jusqu'à pour votre droit de le dire.Tayna Hamway @TaHamway
28 Followers 5K FollowingBenis Ako @ako_benis
43 Followers 47 Followingmhdirnjbr @madiranjbar
32 Followers 101 FollowingFrancois Oustry @francois_oustry
3K Followers 5K Following "A wealth of information creates a poverty of attention" - Herbert A. Simon | AI & Robust Human Decision MakingDominique Montel @dominiquemontel
1 Followers 352 Followinggrumpy @grumpyfr
155 Followers 588 FollowingAbdel Jie @TheObserverJi
13 Followers 249 FollowingDjamé.. @zehavoc
6K Followers 3K Following Associate professor in NLP, engaged citizen. Tweeting about work, life and stuffs that I care about. All my tweets can be used freely. Personal account.Inria Paris NLP (ALMA.. @InriaParisNLP
2K Followers 218 Following Twitter account of ALMAnaCH, the Inria Paris NLP research team. @[email protected]Yann LeCun @ylecun
710K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingGrzegorz Chrupała �.. @gchrupala
6K Followers 1K Following Associate Professor at Tilburg University Computational Linguistics • Machine LearningMartin Haspelmath @haspelmath
9K Followers 2K Following professional linguist who studies patterns in the diversity of the world‘s languagesMiryam de Lhoneux/ @m.. @mdlhx
2K Followers 1K Following #NLProc assistant prof @CW_KULeuven, PI @lagom_nlp. I like syntax more than most people. Also multilingual NLP, interpretability, mountains and beer. (She/her)Antonis Anastasopoulo.. @anas_ant
3K Followers 2K Following Assist. Prof at George Mason CS #nlproc MT, ASR, and documentation of endangered languages.Thomas Wolf @Thom_Wolf
68K Followers 4K Following Co-founder and CSO @HuggingFace - open-source and open-scienceClémentine Fourrier .. @clefourrier
3K Followers 301 Following Leaderboards & evals research @HuggingFace 🐍✨ "The future is already here, it’s just not very evenly distributed" (Gibson)Benjamin Muller @ben_mlr
812 Followers 2K Following Research in AI. Focusing on scaling models to the largest number of languages. Postdoc at FAIR @metaai.Pedro Ortiz Suarez @pjox13
634 Followers 791 Following Senior Research Scientist at the Common Crawl Foundation. Weird coffee person ☕️, runner 🏃🏻♂️. (he/him) 🇫🇷🇪🇺🇨🇴Alexis Conneau @alex_conneau
24K Followers 111 Following Audio AGI Research Lead @OpenAI - GPT-Next - Past: XLM, Unsupervised ASR, Unsupervised MT, Wav2vec 2.0/XLSR, MUSE, Unsupervised cross-lingual transferRachel Bawden @RABawden
652 Followers 208 Following Researcher in NLP in the ALMAnaCH project-team at Inria ParisLaurent Romary 🇪�.. @laurentromary
2K Followers 446 Following Director for scientific information and culture at Inria; ISO, XML, TEI, language resources, digital repositories, lexica, digital humanities, open access.Simon J Greenhill @SimonJGreenhill
4K Followers 2K Following I study how languages and cultures evolve. Primarily with phylogenies and other assorted computational methods. Based at @Biology_UoA. Also @[email protected]Stanford NLP Group @stanfordnlp
144K Followers 179 Following Computational Linguists—Natural Language—Machine Learning @chrmanning @jurafsky @percyliang @ChrisGPotts @tatsu_hashimoto @MonicaSLam @Diyi_Yang @StanfordAILabChristopher Manning @chrmanning
126K Followers 115 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋laurent besacier @laurent_besacie
1K Followers 691 Following Principal Scientist at Naver Labs Europe & Professor at Univ. Grenoble Alpes - now on mastodon [email protected]Seán Ó hÉigeartaig.. @S_OhEigeartaigh
2K Followers 1K Following Director of https://t.co/gCEDoKdKBT at Uni of Cambridge | Researching Big Risks, and impacts of AI & emerging tech. Opinions ownDenis Teyssou @dteyssou
4K Followers 6K Following Geek journalist @AFP Medialab @veraai_eu #innovation manager @InVID_EU @WeVerify verification plugin founder/maker #mediastudies #disinformation #designthinkingSarah Bénière @sarahbeniere
35 Followers 97 Following R&D Engineer at @Inria (ALMAnaCH team) | former TNAH (prom. 2023, @Ecoledeschartes) and ECMA (2021, @LermaAmu) | interested in DH, stylistics and open scienceBiswesh Mohapatra @bis1602
110 Followers 200 Following Multimodal Dialog Systems | PhD Student @Inria | Previously student of @IIITB_official | Interned @IBMResearch, @Siemens | GSOC 2018Jose G Moreno @jgmorenof
323 Followers 711 FollowingLaure Soulier @LaureSoulier
914 Followers 503 Following Associate professor Sorbonne University Information retrieval, NLP, Deep Learning Team @mlia_isir - Sorbonne universitéNaomi Saphra @nsaphra
7K Followers 1K Following Waiting on a robot body. ML/NLP. All opinions are universal and held by both employers and family. Same username on every lifeboat off this sinking ship.Anna Rogers 🇺🇦�.. @annargrs
9K Followers 863 Following Associate professor @ITUkbh: LLM interpretability, generalization, AI & society. Co-editor-in-chief @ACLRollingReviewolivia tambou @oliviatambou
1K Followers 1K Following Senior Lecturer at @Paris_Dauphine, @PSL_univ #dataprotection #privacy #EuropeanLaw, #rtbf, #GDPR, #RGPD, #IA, #AI #dataethics, éditrice @blogdroiteuropeÉditions du Collège.. @EditionsCdF
3K Followers 511 Following Éditer la recherche en train de se faire @cdf1530Laurence Goussu @laurence_goussu
652 Followers 1K Following Responsable Veille et Influence @Inria Passionnée par l'actualité et les enjeux scientifiques et sociétaux de la rechercheLaure Aït-Ali @LaureAitAli
321 Followers 188 Following Responsable #innovation et partenariats @inria_Bordeaux #startup #DeepTech #innovation #numerique #IA #Inria #NouvelleAquitaineGillesMoyse @GillesMoyse
1K Followers 150 Following CEO of @RecitalAI, PhD in #AI, author, @SciencesPo teacher, @AIParis awardee, #G20 Entrepreneur, #Napoleons speaker, happy father of 2Glenn Roe @glennhroe
8K Followers 863 Following Professor of French Literature & Chair of Digital Humanities @Sorbonne_Univ_ • Co-director, Voltaire Lab, @VoltaireOxford • https://t.co/6UrzZXuSJw…David Ifeoluwa Adelan.. @davlanade
2K Followers 1K Following @DeepMind Academic Fellow @uclcs, incoming assistant Professor @mcgillu, Canada CIFAR AI Chair @CIFAR_News | interested in multilingual NLP | Disciple of JesusMagalie Quet @MagalieQuet
26 Followers 106 Following@jbcamps.bsky.social @Jbcamps
1K Followers 1K Following Assoc. Prof. Computational Philology at @Ecoledeschartes|@psl_univ Find me at : @jbcamps.bsky.socialFloriane Chiffoleau �.. @MissBrutus
114 Followers 120 Following Master's degree in Late Modern History and TNAH graduate Now, PhD candidate in Digital Humanities at @Inria/@LeMansUniv TEI enthusiast Movies/TV Shows loverKarën Fort (she/her) @KarnFort1
431 Followers 347 Following Maîtresse de conférences en informatique : ressources langagières et éthique pour le TAL. @[email protected]daniel stoekl ben ezr.. @d_stoekl
983 Followers 858 Following computational humanist. Ancient Hebrew and Aramaic. EPHE, Université PSL. @[email protected]Lucile Moreno @lucile_acm
252 Followers 381 Following 💻 Communication, Sciences, Innovation & Médiation scientifique @Inria_parisThibault Clérice (po.. @PonteIneptique
1K Followers 580 Following Starting researcher @InriaParisNLP #data #dh #digiclass #htr_united #latinMaureen de Seyssel @Maureendss
512 Followers 638 Following PhD from @CoML_ENS in speech, ml and cognition. Ex research intern @MetaAI. @CoML_ENS. unsupervised (multilingual) speech representationsCollège de France @cdf1530
65K Followers 55 Following "Docet (omnes) omnia" 😊 Enseigner (à tous) le savoir en train de se constituer dans les #Sciences, les #Arts & #Lettres | @psl_univOpenGPT-X @OpenGPTX
639 Followers 171 Following Our collaboration between science & industry trains large-scale AI language models to drive innovative language application services for businesses Europe-wide.CoML (Cognitive Machi.. @CoML_ENS
345 Followers 127 Following Twitter account for the Cognitive Machine Learning lab (CoML) at @ENS_ULM (LSCP) led by Emmanuel Dupoux 🧠 👶 💻 🗣Rishika Bhagwatkar @rishika2110
96 Followers 164 FollowingLaurie Burchell @very_laurie
320 Followers 1K Following PhD student at Oilthigh Dhùn Èideann. I do data wrangling for under-served languages.Nikita Moghe @nikita_moghe
940 Followers 1K Following PhD student at CDT in NLP, University of Edinburgh. Prev: IIT Madras | University of Mumbai. She/her. On the industry job marketJesujoba Alabi @alabi_jesujoba
258 Followers 733 Following PhD Student @LstSaar & @SIC_Saar, doing natural language processing #NLProc | prev @InriaParisNLP | @UniIbadan @bowenuniversity alumnus | Ọmọ Jesu |Ọmọ OgbomọṣọAlexis Palmer @lexicutioner
818 Followers 2K Following Computational linguist, CU Boulder Ling. Low-resource & endangered languages, lang documentation, computational discourse and semantics. Musician. she/herrian @riantouchent
59 Followers 73 Following PhD student @ INRIA Paris - Team @InriaParisNLP / Working on information extraction on clinical data using language modelsEmmanuelle Marcadé @EmmaMrcd
581 Followers 536 Following Philanthrope des internets 💻 (elle/she) #SocialMediaManager d'@Inria 🚀 Ici, je tweete #socialmedia, #tech et #communication de manière générale.Villemonte de la Cler.. @DeVillemonte
9 Followers 0 FollowingPedro’s Coffee @pjoxcoffee
108 Followers 563 Following 🇫🇷🇨🇴🇪🇺 Weird coffee person ☕️ and marathon runner 🏃🏻♂️. Tweets in English, Spanish and French. He/HimAmsterdamNLP @AmsterdamNLP
4K Followers 348 Following Tweeting about NLP research, events and opportunities in Amsterdam -- run by @wzuidema and others.Kelly Christensen @KCdemusicologie
87 Followers 110 Following Research Engineer @SciencesPo | Musicology PhD @Stanford | #DigitalHumanitiesOliver Lemon ( @olive.. @oliverlemon
3K Followers 3K Following Chief AI Officer and Co-founder, Alana AI Ltd. Academic Co-Lead of UK National Robotarium. Professor, Director of Interaction Lab: conversational AI and LLMs.Nikolay Bogoychev @XapaJIaMnu
153 Followers 86 Following Postdoc @ University of Edinburgh, alternating between writing matrix matrix multiplications and Chinese characters. https://t.co/2aFhxL1yWRJulien Diaz @Walrus12222
87 Followers 165 Followingeric fleury @fleuryeric
515 Followers 259 Following Director of the Inria Paris centre (@inria @inria_Paris)Michela Russo @Michela_Russ0
1K Followers 4K Following Professeure #Linguistique #Dialectologie #Phonologie. Secrétaire scientifique du CSI-INSHS, #Égalité #VSS Ré-élue #CID 50 @CNRS "Créer, c’est vivre deux fois".Lucas Terriel @TerreLuca
94 Followers 248 Following Web & ML engineer @Ecoledeschartes | ex R&D eng @InriaParisNLPHugo Scheithauer 🏵.. @HugoSchtr
219 Followers 383 Following PhD Candidate, ALMAnaCH, Inria Paris. #DH 🧑💻 Document layout analysis, automatic text recognition, NLP, #TEI. Love playing music on my free time. 🎹Congratulations to Tú Anh Nguyễn who successfully defended his PhD last Tuesday on “Spoken Language Modeling from Raw Audio” supervised by @bensagot and @DupouxEmmanuel (@AIatMeta)! 🍾👨🎓
[#Parution] Benoît Sagot, “Apprendre les #langues aux machines”, @EditionsCdF, coll. “Leçons inaugurales”, en librairie à partir d’aujourd’hui college-de-france.fr/fr/editions/le… @lcdpu @cdf1530 @bensagot #apprentissage #IA #chatGPT #informatique
Wissam Antoun (@wissam_antoun), Benoît Sagot (@bensagot), Djamé Seddah (@zehavoc). From Text to Source: Results in Detecting Large Language Model-Generated Content arxiv.org/abs/2309.13322
Niyati Bafna (@BafnaNiyati), Cristina España-Bonet, Josef van Genabith, Benoît Sagot (@bensagot) and Rachel Bawden (@RABawden). When your Rich Cousin Has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages hal.science/hal-04523029
Lydia Nishimwe (@LydiaNishimwe), Benoît Sagot (@bensagot), Rachel Bawden (@RABawden). Making Sentence Embeddings Robust to User-Generated Content hal.science/hal-04520909
Nathan Godey (@nthngdy), Éric de La Clergerie (@DeVillemonte), Benoît Sagot (@bensagot) On the Scaling Laws of Geographical Representation in Language Models arxiv.org/abs/2402.19406
🤩📄 We are delighted that 8 papers from the team have been accepted at @LrecColing 2024! Have a read through the titles and camera-ready versions here (in no particular order):
Congratulations to Paul-Ambroise Duquenne (@duquenne_pa) who successfully defended his PhD last Thursday on “Sentence Embeddings for Massively Multilingual Speech and Text Processing” supervised by @bensagot and @SchwenkHolger (@AIatMeta)! 🥳👨🎓🍾
[#Média 📰] Comment fonctionnent les #algorithmes que l'on trouve au cœur de la plupart des systèmes d'#IA ? Réponse avec @bensagot et @RABawden (@InriaParisNLP) dans le @maglarecherche : "Dans les arcanes des modèles de langue". Réservé aux abonnés ⤵ larecherche.fr/dans-les-arcan…
#PrixIJC 📢 Découvrez le portrait d’Anne Canteaut, directrice de recherche en informatique à @Inria, spécialisée dans la cryptographie, qui recevra le 7 mars le Prix 2023 « Femme scientifique de l’année » 👉 swll.to/kChuFu
🏆 #PrixIJC | 👏 Félicitations à Anne Canteaut, lauréate de notre Prix Irène Joliot-Curie, dont la cérémonie se déroule ce soir. Directrice de recherche en informatique @Inria, elle revient sur son parcours et sa vision des femmes en sciences. 👉 swll.to/AnneCanteaut
#PrixIJC 🥇 | Félicitations à Anne Canteaut (équipe-projet COSMIQ @inria_paris), spécialiste de #cryptographie qui recevra ce soir le Prix Irène Joliot-Curie 2023 dans la catégorie "Femme scientifique de l’année". Découvrir son portrait ▶ enseignementsup-recherche.gouv.fr/fr/portrait-d-…
[🔴LIVE] 🏆#PrixIJC | Remise du prix de la Femme scientifique de l’année par @sretailleau à Anne Canteaut, directrice de recherche en informatique @Inria Cc @sup_recherche @AcadSciences @AcadTechnolog @citedessciences
[#Média 📰] Anne Canteaut, chercheuse en cryptographie (équipe COSMIQ) et lauréate 2023 du Prix Joliot-Curie "Femme scientifique de l’année" : 💬"Les progrès en recherche naissent de la confrontation des idées"💡. Lire son portrait dans @Chut_magazine ⤵️ chut.media/womenintech/an…
@ylecun Two possible approaches out of the text tokenisation tarpit: Differentiable tokenisers (like MANTa), and tokenisation free models like ByT5, MegaByte, Byteformer etc. Sidenote: The minhash based sub word tokenisation scheme from pNLP-Mixer is also super interesting.
Text tokenization is almost as much of an abomination for text as it is for images. Not mentioning video.
We will see that a lot of weird behaviors and problems of LLMs actually trace back to tokenization. We'll go through a number of these issues, discuss why tokenization is at fault, and why someone out there ideally finds a way to delete this stage entirely.
We're excited for the final seminar in the Collège de France series as part of @bensagot’s annual chair: 9/2/24 at 11am CET: Yann Le Cun, "L'IA axée sur les objectifs : vers des machines capables d'apprendre, de raisonner et de planifier" @ylecun @cdf1530 @AIatMeta @nyuniversity
👏 #HDR | Toutes nos félicitations à Gaëtan Leurent (@cryptosaurus6) de l'équipe-projet COSMIQ qui a soutenu son habilitation à diriger des recherches. Ses travaux portent sur la "Cryptanalyse symétrique au-delà des primitives" 👉 theses.hal.science/tel-04406617v1
Next seminar in the Collège de France series (as part of @bensagot’s annual chair position): 26/01/24 at 11am CET: Elena Cabrio on "Analyse automatique de l'argumentation dans les débats politiques" @ECabrio @cdf1530 @Univ_CotedAzur @inria_sophia @Laboratoire_I3S @wimmics