Kyle Lo @kylelostat
#nlproc #hci leading data research @allen_ai, he/him, bluesky https://t.co/5Hm9cx3Urz kyleclo.github.io Seattle, WA Joined January 2019-
Tweets408
-
Followers2K
-
Following1K
-
Likes2K
huge gift for the community😊 not only will this be highly valuable for LM research, i'd like to see more projects like SciA11y dl.acm.org/doi/10.1145/34… enabled by this
huge gift for the community😊 not only will this be highly valuable for LM research, i'd like to see more projects like SciA11y dl.acm.org/doi/10.1145/34… enabled by this
Talk: "OLMo: Findings of Training an Open LM" from Hanna Hajirshizi at AI2 from OSGAI. Extremely interesting overview of the 4 parts (Data, Training, Adaptation, Eval) of the OLMo open LLM project. Rare insight into how these processes work at scale. youtube.com/watch?v=qFZbu2…
also special call out to @davidjwadden who is our MMLU whisperer 🦅
also special call out to @davidjwadden who is our MMLU whisperer 🦅
Here's OLMo 1.7-7B We figured out how to fix the MMLU score for the first OLMo 7B model when training the bigger one, so we got you OLMo 1.7-7B. Better data (Dolma 1.7) + staged training = 24 point increase. Oh it has 2x the context length too (4096) huggingface.co/allenai/OLMo-1…
What does it take to get a good MMLU score? Turns out: decent data, instructions in pretraining, fuzzy dedup, and quality filtering. just dropped OLMo 1.7-7b… nice perf lift over 1.0! Blog: blog.allenai.org/olmo-1-7-7b-a-… Model: huggingface.co/allenai/OLMo-1… Data: huggingface.co/allenai/dolma
notable stuff: 🦉ton of perf boost from mixing instruct data at end (e.g., flan) 🐋anneal learning rate (Fig 9b in arxiv.org/abs/2403.08763) 🐞changing data mix boosts MMLU at some cost to other evals 🍇huggingface.co/allenai/dolma 🧀huggingface.co/allenai/OLMo-1…
notable stuff: 🦉ton of perf boost from mixing instruct data at end (e.g., flan) 🐋anneal learning rate (Fig 9b in arxiv.org/abs/2403.08763) 🐞changing data mix boosts MMLU at some cost to other evals 🍇huggingface.co/allenai/dolma 🧀huggingface.co/allenai/OLMo-1…
psa 🔔 dolma license now ODC-BY to match c4 and s2orc
🌟Several dataset releases deserve a mention for their incredible data measurement work 🌟 ➡️ The Pile (arxiv.org/abs/2101.00027) @nabla_theta @BlancheMinerva ➡️ ROOTS (arxiv.org/abs/2303.03915) @HugoLaurencon++ ➡️ Dolma (arxiv.org/abs/2402.00159) @soldni @kylelostat 14/
this is the one🍪
follow-up to our work on BooookScore: 🐋prev, we evaluated summary coherency, 🦉now, we're evaluating faithfulness, omissions, etc which is hard cuz it requires localizing summary generations within original source (>100k tokens) come chat w us at @iclr_conf 🐙
follow-up to our work on BooookScore: 🐋prev, we evaluated summary coherency, 🦉now, we're evaluating faithfulness, omissions, etc which is hard cuz it requires localizing summary generations within original source (>100k tokens) come chat w us at @iclr_conf 🐙
PS: if you are also attending GenLaw and are looking for opportunities to research at the intersection of AI, Law, and Policy, let's chat 😊
PS: if you are also attending GenLaw and are looking for opportunities to research at the intersection of AI, Law, and Policy, let's chat 😊
It’s finally here 🎉🥳 In case you missed us, MosaicML/ Databricks is back at it, with a new best in class open weight LLM named DBRX. An MoE with 132B total parameters and 32B active 32k context length and trained for 12T tokens 🤯
truly cursed timeline 😵💫 @ReviewAcl reviews due Mar 20 @COLM_conf abstract deadline Mar 22 @ReviewAcl reviews released Mar 26 @COLM_conf submission deadline Mar 29 @ReviewAcl rebuttal period closes Mar 30
one of my favorite aspects of this project is that it shows careful reuse of high quality "older" datasets is still effective today🦉 we may think "instructions" are relatively recent trend in NLP but some of the datasets we repurpose date back to 2004! 🎂
one of my favorite aspects of this project is that it shows careful reuse of high quality "older" datasets is still effective today🦉 we may think "instructions" are relatively recent trend in NLP but some of the datasets we repurpose date back to 2004! 🎂
LMs can generate plain language summaries. For some audiences, automated simplification of complex text can improve the reading experience. But what of users with more subject matter expertise? Our #CHI2024 paper studies benefits & pitfalls of LMs for simplifying science texts.
LMs can generate plain language summaries. For some audiences, automated simplification of complex text can improve the reading experience. But what of users with more subject matter expertise? Our #CHI2024 paper studies benefits & pitfalls of LMs for simplifying science texts.
can LMs help us write expository answers to scientific research questions? excited to share our work led by @brunchavecmoi. we recruited NLP folks to work with an LM to answer research questions and logged successes/failures in sustained interaction traces🦉
can LMs help us write expository answers to scientific research questions? excited to share our work led by @brunchavecmoi. we recruited NLP folks to work with an LM to answer research questions and logged successes/failures in sustained interaction traces🦉
New Resource: Foundation Model Development Cheatsheet for best practices We compiled 250+ resources & tools for: 🔭 sourcing data 🔍 documenting & audits 🌴 environmental impact ☢️ risks & harms eval 🌍 release & monitoring With experts from @AiEleuther, @allen_ai,…
for those looking for instruction-tuned OLMo👇
for those looking for instruction-tuned OLMo👇
DM me if you're interested in: 🐋creating high-quality pretraining datasets 🐊studying data's impact on LM capabilities 🦉tools for sensemaking over large corpora 🐡adapting LMs to specialized domains like science 🐈evaluation through human interaction
DM me if you're interested in: 🐋creating high-quality pretraining datasets 🐊studying data's impact on LM capabilities 🦉tools for sensemaking over large corpora 🐡adapting LMs to specialized domains like science 🐈evaluation through human interaction
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (Dolma 🍇), OSS is fun, @QueerInAI organizer 🤖☕️🍕they/them (views mine, not my employer’s)AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxAkari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Ana Marasović @anmarasovic
4K Followers 604 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷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 🌈Allen Institute for A.. @allen_ai
54K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLBill Yuchen Lin 🤖 @billyuchenlin
6K Followers 2K Following Research @allen_ai. I evaluate (multi-modal) LLMs, build agents, and study the science of LLMs. Previously: @GoogleAI & @MetaAI FAIR @nlp_uscKayo Yin @kayo_yin
8K Followers 560 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Sam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.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).Ofir Press 🖋 @OfirPress
10K Followers 3K Following I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.Prithviraj (Raj) Amma.. @rajammanabrolu
5K Followers 519 Following Interactive & grounded AI, RL, NLP. Assistant Prof @UCSanDiego. Research Scientist @DbrxMosaicAI. Prev: @allen_ai, @GeorgiaTechSarah Wiegreffe @sarahwiegreffe
4K Followers 984 Following At @allen_ai @ai2_aristo @uwnlp. Research in language model transparency & interpretability. PhD from @mlatgt @icatgt @gtcomputing. Views my own.Swaroop Mishra @Swarooprm7
5K Followers 894 Following Research Scientist @GoogleDeepMind (Gemini). Pioneering LLM Research 🔥. Instruction tuning, Factuality, Reasoning and next gen Product. Opinions my own.Tuhin Chakrabarty @TuhinChakr
2K Followers 620 Following Newly minted Ph.D. from @ColumbiaCompSci studying creativity. Ex affiliations: @GoogleDeepmind @SFResearch @allen_aiShruti Rijhwani @shrutirij
4K Followers 499 Following * Research Scientist @GoogleDeepMind * #NLProc research * PhD from @LTIatCMU * Amateur woodworker, scuba diver, foosball playerNaomi 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.MignonKathleen @4uyHO1Hn90n70j
0 Followers 19 FollowingZeigh @ZeighxJzO91
0 Followers 19 FollowingDeyan Ginev @dginev
1K Followers 390 Following Researching NLP for Math-rich documents. arXiv syntax spelunking. LaTeXML developer. creator of https://t.co/3d4VTPw7LjLyla-grace Lamarque @LamarqueLy44745
85 Followers 5K FollowingKevin Feng @kjfeng_
408 Followers 373 Following PhD student @hcdeUW @SocFuturesLab; social computing, collaboration, interactive ML; prev @MSFTResearch @PrincetonCITP @PrincetonCS; also @[email protected] 🐘DominicGreen @5q80Di4ChFkc1
0 Followers 110 FollowingLilithHerbert @aPrC6Wc0A4Yag
0 Followers 175 FollowingDeniz Birlikci @denizbirlikci
28 Followers 121 Following cs + ai @CarnegieMellon, scholar @neo, prev @MercedesAMGF1Quentin Anthony @QuentinAnthon15
999 Followers 129 Following I make models more efficient. Google Scholar: https://t.co/kzVsAKPdrpPensé FFun @inftyCategory
96 Followers 6K FollowingAbdulrahman Tabaza @embed_dim
4 Followers 809 Following enjoyer of various vector spaces, encoders and modalitiesDaniel Kořínek @DanielKonek8
0 Followers 12 Following𝕋𝕒𝕥𝕤𝕦�.. @tatsuru_kikuchi
367 Followers 3K Following Research Officer at Faculty of Economics, The University of Tokyo. Keywords: Entrepreneur/OpenAI/Quantum/Crypto/Analytics/Consulting. Views are my own. Jungo Kasai 笠井淳.. @jungokasai
2K Followers 386 Following Co-founder & CTO @kotoba_tech: "Towards End-to-End Speech Foundation Models." | PhD from @nlpnoah at @UW | IBM PhD Fellow | 孫正義育英財団生 | @Yale UndergraduateAzoth @Azoth42
49 Followers 383 FollowingPete @epwalsh
52 Followers 88 Following Research Engineer at @allen_ai. Lead engineer for OLMo pretraining.bofeng @bofenghuang1
67 Followers 301 Followingzirui @zirui3
37 Followers 949 FollowingSophie @lebrechts
901 Followers 839 Following COO @allen_ai formerly AI/ML @Apple, SVP Strategy & Ops https://t.co/4Z5RuqSEkZ, PhD from @BrownUniversity, post-doc @CarnegieMellonKavel Rao @kavel_r
56 Followers 224 Following BS/MS student and researcher at @uwcse @uwnlp Incoming intern at @databricksexns @euxenus
1K Followers 720 Following building a Second Brain, dissecting the Global Brain, and merging with the twoJenna Russell @jennajrussell
1 Followers 76 Following Incoming Cs PhD Student @umass advised by @MohitIyyer, currently @BankofAmerica NLP, formerly @CornellCISDan Saattrup Nielsen @saattrupdan
16 Followers 78 Following Senior AI Specialist at the Alexandra InstituteArif Ahmad @arif_ahmad_py
281 Followers 7K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIAndrew Drozdov @mrdrozdov
2K Followers 1K Following RAG at @MosaicML x @Databricks 🧱 Prev: @UMass_NLP, @Google, @IBMBailey Kuehl @BaileyKuehl3
1 Followers 12 FollowingAlexander Wan @alexwan55
475 Followers 944 Following CS at Berkeley; @BerkeleyML @BerkeleyNLP; NLP researchKun (Kevin) SUN @Sharp_K_Sun
220 Followers 2K Following Scientist Researcher @ Tübingen University and Professorial Research Fellow @ Fudan University, and interested in LLMs, NLP, and computational cognition .Data Science Research.. @ArionDas
360 Followers 2K Following Deep Learning || Research Work on ML, DL || Large Language Models || GANs || RAG || Competitive Programming || Generative AI || Optimization Algorithms || IIITRTERRY TERRY @TTerry55348
80 Followers 1K FollowingKyle Wiggers @Kyle_L_Wiggers
65K Followers 4K Following Technology journalist. Senior Enterprise Reporter @TechCrunch ([email protected]). Pronouns: he/him. Mastodon: https://t.co/wesC0GePagChenxin An @AnChancy46881
117 Followers 188 Following PhD Candidate @ HKU NLP Awardee of Hong Kong PhD Fellowship Scheme (HKPFS)Brett Larsen @_BrettLarsen
419 Followers 332 Following Sr. Research Scientist @DbrxMosaicAI | Guest Researcher @FlatironInst @NYU_CNS | Efficient deep learning + better algorithms for data scienceIbrahim Ahmad @Ibrahim63433664
86 Followers 3K FollowingPutra Manggala @pmangg
503 Followers 4K Following researcher @amlabuva, previously @shopify, @guavus, @adgear, @mcgillu. Not fun at parties.(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingLuca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (Dolma 🍇), OSS is fun, @QueerInAI organizer 🤖☕️🍕they/them (views mine, not my employer’s)Yann LeCun @ylecun
712K Followers 719 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxAndrej Karpathy @karpathy
980K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistAna Marasović @anmarasovic
4K Followers 604 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷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 🌈Allen Institute for A.. @allen_ai
54K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLAI at Meta @AIatMeta
532K Followers 255 Following Together with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.Graham Neubig @gneubig
31K Followers 588 Following Associate professor at CMU, studying natural language processing and machine learning.Sasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzBill Yuchen Lin 🤖 @billyuchenlin
6K Followers 2K Following Research @allen_ai. I evaluate (multi-modal) LLMs, build agents, and study the science of LLMs. Previously: @GoogleAI & @MetaAI FAIR @nlp_uscKayo Yin @kayo_yin
8K Followers 560 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Christopher Manning @chrmanning
127K Followers 116 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋Sam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Deyan Ginev @dginev
1K Followers 390 Following Researching NLP for Math-rich documents. arXiv syntax spelunking. LaTeXML developer. creator of https://t.co/3d4VTPw7LjKevin Feng @kjfeng_
408 Followers 373 Following PhD student @hcdeUW @SocFuturesLab; social computing, collaboration, interactive ML; prev @MSFTResearch @PrincetonCITP @PrincetonCS; also @[email protected] 🐘Quentin Anthony @QuentinAnthon15
999 Followers 129 Following I make models more efficient. Google Scholar: https://t.co/kzVsAKPdrpRose @rose_e_wang
2K Followers 238 Following NLP & Education @stanfordnlp 🌲 Prev: 2020 MIT 🦫, Google Brain 🧠, Google Brain Robotics 🤖Stephanie Bell @the_sbell
294 Followers 1K Following Senior Research Scientist on AI, Labor & Economy with the Shared Prosperity Initiative at @partnershipai all views my own.Partnership on AI @PartnershipAI
31K Followers 771 Following A non-profit bringing together academic, civil society, industry, & media organizations to address the most important and difficult questions concerning AI.Mistral AI @MistralAI
91K Followers 0 Following Fast, open-source and secure language models. Join us https://t.co/INALdNGvCPTogether AI @togethercompute
27K Followers 304 Following The future of AI is open-source. Let's build together.Adam Day @ClearSkiesAdam
1K Followers 1K Following CEO and founder of Clear Skies, the leading provider of papermill detection services. #papermillalarmKyle Wiggers @Kyle_L_Wiggers
65K Followers 4K Following Technology journalist. Senior Enterprise Reporter @TechCrunch ([email protected]). Pronouns: he/him. Mastodon: https://t.co/wesC0GePagNouran Soliman @nouranmsoliman
422 Followers 2K Following PhD Candidate @MIT_CSAIL @haystack_csail @MITEECS @MIT | HCI | Online Safety & Trust | Social Computing | Social Media | AIBrett Larsen @_BrettLarsen
419 Followers 332 Following Sr. Research Scientist @DbrxMosaicAI | Guest Researcher @FlatironInst @NYU_CNS | Efficient deep learning + better algorithms for data scienceAkhil Arora @aroraakhilcs
216 Followers 203 Following CS PhD @EPFL 🇨🇭| Ex Research Scientist @americanexpress @Xerox | Data Science | NLP | Graph ML | Networks | Causality | 🥾🏔️🚴♂️🏋️♂️⚽️🎾 🎸| he/him/hisConference on Languag.. @COLM_conf
2K Followers 6 Following https://t.co/GhGCMEoa4A Abstract submission: March 22, 2024Sebastian Majstorovic @storytracer
2K Followers 813 Following Digital Historian & Data Consultant | https://t.co/fev0QjCWjp | https://t.co/yqa5eIfpTu | Co-Founder @sucho_orgAlon Albalak @AlbalakAlon
887 Followers 465 Following CS PhD candidate at @ucsbNLP. Research: Data-centric AI, Efficiency in ML, NLP.Leo Gao @nabla_theta
5K Followers 339 Following Alignment researcher. cofounder & head of alignment memes @ EleutherAI. currently RE @ OpenAI. Let's make the future awesome.Thomas Durieux @thodurieux
166 Followers 179 FollowingYasumasa Onoe @yasumasa_onoe
339 Followers 281 Following Software Engineer @GoogleAI working on vision and language researchSophie @lebrechts
901 Followers 839 Following COO @allen_ai formerly AI/ML @Apple, SVP Strategy & Ops https://t.co/4Z5RuqSEkZ, PhD from @BrownUniversity, post-doc @CarnegieMellonAnanya Harsh Jha @AnanyaHarsh
393 Followers 2K Following Predoctoral Young Investigator at @ai2_allennlp @allen_aiTransactions on Machi.. @TmlrOrg
5K Followers 3 Following Transactions on Machine Learning Research (TMLR) is a new venue for dissemination of machine learning researchMichael Xieyang Liu @lxieyang
1K Followers 2K Following Research Scientist @GoogleAI People + AI Research. HCI + AI + Programming Support + Sensemaking. ex @SCSatCMU @UMich @MSFTResearch @GoogleAI. He/himInterconnects @interconnectsai
2K Followers 1 Following What you need to know about AI research trends, from @natolambert Wednesday mornings weekly, sometimes extra posts.Hailey Schoelkopf @haileysch__
3K Followers 814 Following she/her | research scientist @aiEleuther | LLM training/infra, eval, data | LM Evaluation Harness maintainerLiangming Pan (on job.. @PanLiangming
1K Followers 717 Following Postdoc at @ucsantabarbara @ucsbNLP | Ph.D. from @NUSingapore @wing_nus | Researcher in #NLProc | Interests: Reasoning, QA, Generation, Fact CheckingValentin Hofmann @vjhofmann
968 Followers 228 Following Young Investigator (Postdoc) @allen_ai @ai2_allennlp | Formerly @UniofOxford @CisLMU @stanfordnlp @GoogleDeepMindCody Blakeney @code_star
3K Followers 825 Following Head of Data Research @MosaicML / @databricks | Formerly Visiting Researcher @ Facebook | Ph.D | #TXSTFOOTBALL fan | https://t.co/4G6Jf3at5wRohan Jha @Robro612
70 Followers 221 Following Currently MS CS @UTAustin; previously BS AI @carnegiemellon. Interested in Information Retrieval and NLPSky CH. Wang @skychwang
697 Followers 1K Following CS PhD Candidate @Columbia. @ColumbiaNLP & Computational Social Science. @NSF GRFP fellow. Formerly @GoogleAI @MSFTResearch @AmazonScience @NASA @UMich.Shangbin Feng @shangbinfeng
1K Followers 1K Following PhD student @uwcse @uwnlp. Understanding and expanding the knowledge abilities of LMs, social NLP, networks and structures. he/him. #水文学家Ian Magnusson @IanMagnusson
250 Followers 294 Following Predoctoral Young Investigator on AllenNLP at @allen_ai. Working on domain adaptation, reproducibility, and evaluation in NLP.Venkat @_venkatasg
185 Followers 108 Following Ph.D. candidate at UT Austin studying intergroup bias in communication. Also on https://t.co/khmUd6ZOcI and https://t.co/M8inNG6umlSaurabh Shah @saurabh_shah2
494 Followers 989 Following ML Engineer @Apple /Siri NLU, prev @allen_ai @Penn …. 🎤dabbler in standup comedy and music 🎸… 🐈⬛enjoyer of cats 🐈 and mountains🏔️ …he/himHyunwoo Kim @hyunw__kim
1K Followers 438 Following Social Reasoning/Commonsense + AI | Postdoc @allen_ai | PhD @SeoulNatlUniSireesh Gururaja @_sireesh
359 Followers 2K Following Trying to get to know my neighbors, both irl and online. PhD student @LTIatCMU, interested in NLP that lets people keep agency. Former: @kensho, @IBM, @ColumbiaAviya Skowron @aviskowron
335 Followers 479 Following they/them. Head of Policy and Ethics @AiEleuther. Find me in the EleutherAI Discord to chat. Always looking for ways to weave philosophy into my job.Omar Shaikh @oshaikh13
579 Followers 798 Following CS Ph.D. student @Stanford - previously @GeorgiaTech - also @[email protected]Fei Wang @fwang_nlp
920 Followers 2K Following PhD candidate @USC. PhD Fellow @Amazon. Responsible LLM.Kaiser Sun @KaiserWhoLearns
733 Followers 408 Following Ph.D. student at @jhuclsp , human LM that hallucinates. Formerly @MetaAI, @uwnlp and @AWS they/them🏳️🌈Najoung Kim 🫠 @najoungkim
2K Followers 493 Following At @BULinguistics and visiting @GoogleAI part-time. 🤖🔠🐱Peter Jansen @peterjansen_ai
1K Followers 643 Following Associate Professor @uarizona; Visiting Scientist @allen_ai, AI/NLP; EntailmentBank; ScienceWorld; WorldTree; ExplanationBank. Tweets/opinions my own.Be careful if you use wandb features outside of the core experiment logs! We've experienced: - data loss (we can't retrieve data via API that is available in the UI) - API inconsistency (project.sweeps.runs != sweep.runs) - indefinite hangs when uploading/downloading artifacts
📢 Looking for a 1-year postdoc in beautiful Copenhagen! Application due May 31, can start in 2024/09 The project is an ambitious generalization benchmark in collaboration with @tallinzen. Ideal candidate will have CL background, core ML skills, experience building resources. /1
This was one of my favorite talks from the workshop! Truly great insights from @haozhangml, and big thanks to the entire @lmsysorg team for ChatArena
Had to give a talk to some CEOs. They knew way more about LLMs than me. Asked one of them how, he said "I check Chatbot Arena every morning" 😆 New OSGAI talk from Hao Zhang (@haozhangml ) on Chatbot Arena, seemingly the only eval anyone trusts. youtube.com/watch?v=7njmta…
ChatGPT must now check if you are operating a moving vehicle before responding to you
Talk: "OLMo: Findings of Training an Open LM" from Hanna Hajirshizi at AI2 from OSGAI. Extremely interesting overview of the 4 parts (Data, Training, Adaptation, Eval) of the OLMo open LLM project. Rare insight into how these processes work at scale. youtube.com/watch?v=qFZbu2…
I am happy to announce that my paper got a Best Paper Award at #CHI2024! Come to my talk at CHI on Wednesday May 15th at 9:30am (Hawaii Standard Time) to learn more about my work.
🚨 #CHI24 Paper Alert! 🚨 We introduce #meronymity, a novel design paradigm to mitigate social barriers in public social interactions by revealing aspects of identity to balance credibility & privacy @amyxzh @turingmusician @josephcc @karger @hyeonsuukang. arxiv.org/pdf/2402.17847…
... even with smaller data teams, it is possible to upsample datasets such as Wiki, OpenWebMath, high quality code data, instructions, especially during annealing for boosted performance which is what @kylelostat and co. did for the boosted Olmo 1.7 ! blog.allenai.org/olmo-1-7-7b-a-…
I think people some people (not necessarily Jesse) misunderstood why there is a lack of transparency. Meta isn’t afraid of transparency, or giving up secret sauce. Big players will not disclose their data until case law over copyright/fair use is better defined. That doesn’t mean…
This follows the trend of large organizations releasing models and promoting their capabilities, while not providing the information necessary to understand their behavior: the training data. To be clear, this is expected, but also highlights the need for more transparency.
I am super excited about the release of our 8B & 70B LLaMA 3 models! Huge team effort, amazing learning experience, and we're not done - the 405B is still training! #Llama3
It’s here! Meet Llama 3, our latest generation of models that is setting a new standard for state-of-the art performance and efficiency for openly available LLMs. Key highlights • 8B and 70B parameter openly available pre-trained and fine-tuned models. • Trained on more…
@DrJimFan "watershed" how did this become a term we use like this LOL
had to google this to keep up with llm training discourse (subsequently facepalmed because I probably should have figured the latin pattern out bi now)
@soldni @natolambert @rosstaylor90 The blog is correct (sigh...)
Llama3-8B and 70B have dropped!! Extremely grateful to have been part of this journey. More coming soon :) llama.meta.com/llama3/
@kylelostat @zehavoc x.com/ml_perception/…
Excited to share a preview of Llama3, including the release of an 8B and 70B (82 MMLU, should be the best open weights model!), and preliminary results for a 405B model (still training, but already competitive with GPT4). Lots more still to come... ai.meta.com/blog/meta-llam…
Excited to share a preview of Llama3, including the release of an 8B and 70B (82 MMLU, should be the best open weights model!), and preliminary results for a 405B model (still training, but already competitive with GPT4). Lots more still to come... ai.meta.com/blog/meta-llam…
Our teammates consistently cite "the people" as their favorite part of AI2. We're currently looking to hire a superstar to help build out our team and culture! If you want to work with the best people solving the biggest problems, come join the fun! 🪩 boards.greenhouse.io/thealleninstit…