Sarah Wiegreffe @sarahwiegreffe
At @allen_ai @ai2_aristo @uwnlp. Research in language model transparency & interpretability. PhD from @mlatgt @icatgt @gtcomputing. Views my own. sarahwie.github.io Joined September 2013-
Tweets921
-
Followers4K
-
Following984
-
Likes10K
move over meta, the true biggest benefactor of open source machine learning is CHANEL
move over meta, the true biggest benefactor of open source machine learning is CHANEL
Not me thinking ACL was hosting a climbing competition 🧗⛰️
Do you know the ACL mailing list? Apparently, it resets yearly, and you return to it only after you register (and pay). So, our email (which we thought would reach the broad NLP community) about our contamination workshop (conda-workshop.github.io) only reached 227 members...
🚨New Paper Alert🚨 Beware! While personas excel at refining LLM behavior, they can bring deep-rooted biases to the surface, diminishing LLM's core competencies 😲 Our study reveals a surprising finding – Personas can degrade LLMs' reasoning by a massive 70%! 🤯…
OLMo is here! And it’s 100% open. It’s a state-of-the-art LLM and we are releasing it with all pre-training data and code. Let’s get to work on understanding the science behind LLMs. Learn more about the framework and how to access it here: blog.allenai.org/olmo-open-lang…
Congrats to @allen_ai for the excellent release of OLMo It's a true open source end-to-end release: not just • model code • model weights but also • training code • training data (and associated toolkits) • eval toolkits This is pushing the enveloppe of open-source AI 🔥
If you are submitting interpretability work to ICML, you absolutely should not be using the boilerplate broader impact statement. All interpretability papers should include a qualifying disclosure.
ICLRed the bar
To solve difficult problems, do LLMs need to be trained with difficult problems? Not according to this new research from the @ai2_aristo team! Access the paper and the team's public code to learn more:
To solve difficult problems, do LLMs need to be trained with difficult problems? Not according to this new research from the @ai2_aristo team! Access the paper and the team's public code to learn more:
Checkout our recent work on easy-to-hard generalization with LMs, led by outstanding intern @peterbhase :
Checkout our recent work on easy-to-hard generalization with LMs, led by outstanding intern @peterbhase :
Check out our work SelfRefine with @aman_madaan at #NeurIPS2023. I’m not attending this year but bunch of my @allen_ai and @ai2_aristo colleagues are around NOLA, go talk to them!
Check out our work SelfRefine with @aman_madaan at #NeurIPS2023. I’m not attending this year but bunch of my @allen_ai and @ai2_aristo colleagues are around NOLA, go talk to them!
Looking forward to discussing our recent work on using inference-time compute for effective reasoning at #NeurIPS2023! 🗓️ Self-Refine: Iterative Refinement with Self-Feedback, Wed 13 Dec 5 p.m., Great Hall & Hall B1+B2 (level 1) Poster #324 selfrefine.info 🗓️ AutoMix:…
We’re right at the entrance (2A)
We’re right at the entrance (2A) https://t.co/jchHx1kYPA
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K Following
Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳
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 🌈
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.
Luca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (makin Dolma 🍇), open source science fan, @QueerInAI organizer 🤖☕️🍕they/them
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).
Kayo Yin @kayo_yin
8K Followers 556 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵
Naomi 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.
Danish Pruthi @danish037
7K Followers 628 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.
Mark Dredze @mdredze
4K Followers 786 Following John C Malone Professor at @JohnsHopkins @JHUCompSci @jhuclsp @jhumceh; Part time @techatbloomberg (tweets my own) Mastodon @[email protected]
Ana Marasović @anmarasovic
4K Followers 604 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷
Mark Riedl @mark_riedl
32K Followers 1K Following AI for storytelling, games, explainability, safety, ethics. Professor @GeorgiaTech. Associate Director @MLatGT. Time travel expert. Geek. Dad. he/him
Graham Neubig @gneubig
31K Followers 586 Following Associate professor at CMU, studying natural language processing and machine learning.
Jacob Andreas @jacobandreas
14K Followers 958 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJw
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/tvb1VpySfL
Shaily @shaily99
5K Followers 2K Following PhD @LTIatCMU Prev: @GoogleAI @MSFTResearch. Working on ethics and evaluation in #NLProc. Usually ranting, often about research & DEI. 📚 @readsndrants
Bill 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_usc
Christopher Potts @ChrisGPotts
11K Followers 620 Following Stanford Professor of Linguistics and, by courtesy, of Computer Science, and member of @stanfordnlp and @StanfordAILab. He/Him/His.
Mr Collins Harrison @MrCollinsHarri1
641 Followers 676 Following Love yourself enough that other people’s love or hate doesn’t matter to you. You are all you need. i'm a man of Truth and i always put God first in everything
animals kittens @AnimalsK11
14 Followers 103 Following Cute and Funny Cats / Chick Babies / Parot Baby Daily Routine and Funny
KB @katiebowles_
642 Followers 5K Following Advancing AI for Healthcare at Scale at @AbridgeHQ | $150M Series C 🚀 | We're Hiring!
Peter Morales @PeterMoralesX
218 Followers 2K Following Founder of funded Stealth AI Startup. Interested in AI development at the edge? DM.
pengch fan @FanPengch
215 Followers 6K Following
Koushik @koushik_here
720 Followers 5K Following Machine Learning for biology | Deep Learning Data Scientist @Bayer4Crops | Prev: PhD @IowaStateU | he/him
Lam Tung Vo @nolanvo5894
179 Followers 4K Following
Vikram Dutt @vd_
819 Followers 7K Following
Generative AI @generativeaihub
7K Followers 6K Following Inspired by Algorithms, Powered by Imagination: Unleashing the Potential of Generative AI. #GenerativeAI #deeplearning #AI #MachineLearning
Pensé FFun @inftyCategory
108 Followers 6K Following
Guneet Singh Kohli @guneetsk99
455 Followers 3K Following AI Engineer @ GreyOrange, Building Indian LLMs with Odia GenAI Independent Researcher working on variety of random problems.
Pete @epwalsh
51 Followers 88 Following Research Engineer at @allen_ai. Lead engineer for OLMo pretraining.
joe @joe_knows_LEGO
38 Followers 162 Following LEGO Building Architecture // Doctorate (Ph.D.) in Sport Psychology https://t.co/2ZWUaUsSUn
Edwin Simpson @overwired
401 Followers 2K Following Lecturer; Natural Language Processing and Machine Learning. 🏳️🌈🇬🇧🇩🇪
Janhavee Shinde @SJanhavee
56 Followers 2K Following
JHU CLSP @jhuclsp
5K Followers 662 Following Center for Language and Speech Processing at @JohnsHopkins #NLProc #MachineLearning #AI https://t.co/6IXR5OSiDY @[email protected]
Rakesh Dey @RakeshD24137483
32 Followers 509 Following ML theory, Optimization, Statistics, Computer Vision
Christopher Z. Cui @ccui9
23 Followers 22 Following Just a he/him who likes writing and games. I program things sometimes. Master's student @GeorgiaTech
Gagan Jain @gaganjain1582
50 Followers 745 Following Predoc Researcher @GoogleDeepMind | IIT Bombay'22
Mickel Liu @mickel_liu
100 Followers 235 Following research visiting @uwnlp, Prev: @PKU1898, @uoftengineering RL + LLM
Nicholas Lourie @NickLourie
120 Followers 178 Following I build things. 🤖 Doing a PhD at @nyuniversity (@CILVRatNYU) on better empirical methods for deep learning and data science. Advised by @kchonyc and @hhexiy.
Arshad | ارشد ع�.. @arsh14_ali
65 Followers 340 Following ASE @TCS 🧑💼 | Self-Taught Developer. 🎯👨💻
BacklinkGPT @BacklinkGPT
12 Followers 103 Following Automate Your 🔗 Link-Building with AI-Personalized Outreach | AI-Driven Outreach Personalization | One-Click Link Prospecting | Automated Contact Discovery
JEON, SO YEON @soyeon_polisci
187 Followers 375 Following Political Science || Ph.D. student @WashU | | Political Communication, Computational Social Science
Jason Liu @_jasonliu_
28 Followers 274 Following ML, Graphics, RS Art & Design in 3D & 2D, see 'Media' Profile Image by me https://t.co/9pbFgftKIS
CollaborativeDynamics.. @CoDynamicsAI
23 Followers 802 Following Boost all aspects of your business with our bespoke B2B AI solutions in prompt engineering, personas and automation. #AI #Automation #GenerativeAI🚀
Amrit Singh Bedi @amritsinghbedi3
524 Followers 1K Following CS Faculty at UCF (AlignAI Lab), previous @UMD @ARL @IITK Interested in RL, Nonconvex Optimization, AI text Detection, Federated Learning, Robotics
Tran Bao Chi @TranBaoChi7
17 Followers 471 Following Undergrad #DSAI #HUST Research Intern #NLP #VinAIResearch
Eva Louise Marie Gabr.. @e681554349
9 Followers 3K Following
HK @SeeHk
0 Followers 182 Following
Qasim Ali @QasimAliSidhu
168 Followers 1K Following AI First Tech Savvy Technical Customer Support Engineer #AI #GenerativeAI #GenAI #FutureAILeaders #AIFirst
Tom Hope @Hoper_Tom
997 Followers 1K Following Assistant professor and research scientist at AI2 | boosting scientific discovery with AI, NLP, IR, KG, HCI | תום הופ
Nikhil Sharma @nikhilsksharma
229 Followers 612 Following Incoming PhD in HAI @JohnsHopkins | Information Seeking | Disinformation Agents | Copilots for Social Good | PhD @JHUCLSP @JHUMCEH #NLProc
Pranav Kashyap H @pkh39
23 Followers 818 Following An intelligent living spec of dust traveling in the endless cosmos
Andreas Vlachos @vlachos_nlp
5K Followers 1K Following Professor in NLP/ML at @Cambridge_CL, Fellow of @FitzwilliamColl, @ELLISforEurope member
Maxime Peyrard @peyrardMax
213 Followers 279 Following Junior Professor @CNRS (previously @EPFL, @TUDarmstadt) -- AI Interpretability, causality, and interaction flows between LLM, humans, and tools
kumar @kumar__nn
0 Followers 1K Following
Ruairi @ruairiSpain
265 Followers 2K Following
Hitesh Patel @Hitesh_LPatel
165 Followers 892 Following Latest Research Paper Tweets, GenAI Tech lead @Oracle , ML Researcher @NYU
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K Following
Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳
Yoav Artzi @yoavartzi
13K Followers 163 Following Research/prof @cs_cornell + @cornell_tech🚡 / https://t.co/9YnWry7yHs / https://t.co/3VmRSyYm2d / asso. faculty director @arxiv / building https://t.co/f9QkzO5kaC
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 🌈
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.
Tal Linzen @tallinzen
16K Followers 893 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAI
Luca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (makin Dolma 🍇), open source science fan, @QueerInAI organizer 🤖☕️🍕they/them
Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianist
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).
Kayo Yin @kayo_yin
8K Followers 556 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵
William Wang @WilliamWangNLP
14K Followers 717 Following UCSB NLP Lab + ML Center. https://t.co/6TOnqbk6YT https://t.co/KJYhnav3Et Mellichamp Chair Prof. at UCSB CS. PhD @ CMU SCS. Areas: #NLProc, Machine Learning, AI.
Rosanne Liu @savvyRL
33K Followers 966 Following Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS. Writing https://t.co/IbycyGfnDR
Naomi 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.
Sasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGz
Danish Pruthi @danish037
7K Followers 628 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.
Mark Dredze @mdredze
4K Followers 786 Following John C Malone Professor at @JohnsHopkins @JHUCompSci @jhuclsp @jhumceh; Part time @techatbloomberg (tweets my own) Mastodon @[email protected]
Ana Marasović @anmarasovic
4K Followers 604 Following Asst prof @UUtah · Ex @allen_ai @uwnlp postdoc @HD_NLP PhD · she/her 🇭🇷
Mark Riedl @mark_riedl
32K Followers 1K Following AI for storytelling, games, explainability, safety, ethics. Professor @GeorgiaTech. Associate Director @MLatGT. Time travel expert. Geek. Dad. he/him
Pete @epwalsh
51 Followers 88 Following Research Engineer at @allen_ai. Lead engineer for OLMo pretraining.
Clémentine Fourrier .. @clefourrier
3K Followers 301 Following Leaderboards & evals research @HuggingFace 🐍✨ "The future is already here, it’s just not very evenly distributed" (Gibson)
Conference on Languag.. @COLM_conf
2K Followers 6 Following https://t.co/GhGCMEoa4A Abstract submission: March 22, 2024
jack morris @jxmnop
10K Followers 762 Following getting my phd in nlp @cornell_tech 🚠 // academic optimist // tweeting from the snack aisle at trader joes
Andreas Grivas @andreasgrv
379 Followers 550 Following PhD Candidate in Natural Language Processing at the University of Edinburgh.
Gabriele 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.
Inseq @InseqLib
302 Followers 634 Following Open-Source Interpretability for Generative Language Models 🔎 🐛
Sebastian Raschka @rasbt
267K Followers 906 Following Machine learning & AI researcher writing at https://t.co/A0tXWzG1p5. LLM research engineer @LightningAI. Previously stats professor at UW-Madison.
Center for Safe, Expl.. @PennAsset
405 Followers 40 Following A @PennEngineers research center devoted to science and tools for ensuring AI-enabled systems are safe, explainable, and trustworthy
Sahil Verma @Sahil1V
455 Followers 1K Following PhD student @uwcse. Robustness and Interpretability in ML. Former intern at @amazon, @itsArthurAI, @ETH_en, @MIT, @NUSingapore. Undergrad @IITKanpur
Meredith Whittaker @mer__edith
92K Followers 4K Following President of @signalapp, Chief Advisor to @ainowinstitute (Also on Mastodon @[email protected], also on bsky @meredithmeredith.bsky.social)
Archiki Prasad @ArchikiPrasad
967 Followers 819 Following PhD student @uncnlp, advised by @mohitban47 | Undergrad @iitbombay | Prev: @allenai_org @AdobeResearch; Research interests: #NLProc #ML
Philippe Laban @PhilippeLaban
346 Followers 354 Following Research Scientist @salesforce. Working at the intersection of NLP and HCI.
Nouha Dziri @nouhadziri
3K Followers 672 Following Research Scientist @allen_ai / @ai2_mosaic, PhD in NLP/Dialogue 🤖 UofA. Ex Visiting researcher @Mila_Quebec Ex Research intern at @GoogleDeepMind @MSFTResearch
Sahana Ramnath @sahana_ramnath
247 Followers 297 Following Second year PhD student at @USCViterbi / @nlp_usc. Interested in NLP, DL and RL (particularly, interpretability). Obsessed with reading fiction and fantasy.
Jelani Nelson @minilek
22K Followers 184 Following Professor @Berkeley_EECS. Research Scientist (part-time) @GoogleAI. Founder @addiscoder. 🇻🇮🇺🇸🇪🇹
XAI_in_Action_Worksho.. @XAI_in_Action
86 Followers 7 Following Account for "XAI in Action: Past, Present, and Future Applications" Workshop at NeurIPS 2023 https://t.co/dj3QU97YF4
Qinyuan Ye @qinyuan_ye
2K Followers 1K Following 👩💻 Ph.D. student @nlp_usc @CSatUSC @USC_ISI | 🐾 Teaching machines to be more versatile and curious.
Alessandro Stolfo @alesstolfo
677 Followers 399 Following PhD Student @ ETH Zürich in #NLProc | Prev. @oracle Labs
Namgyu Ho @itsnamgyu
1K Followers 326 Following PhD student at OSI LAB @kaist_ai. Working on novel but practical ways to improve LLMs. Previously showed that LLMs are reasoning teachers.
Fan Yin @FanYin63689862
196 Followers 203 Following PhD candidate at UCLA-NLP | former intern at Salesforce Research, Amazon AWS | Robustness/Reliability/Interpretability in NLP
Kavel Rao @kavel_r
57 Followers 222 Following BS/MS student and researcher at @uwcse @uwnlp Incoming intern at @databricks
Momose Oyama @momose123456789
508 Followers 369 Following First-year Ph.D. student at Kyoto University
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
Kevin Meng @mengk20
1K Followers 175 Following @MIT. interested in language models, compbio, and robotics :)
Marius Mosbach @mariusmosbach
713 Followers 877 Following Postdoc @Mila_Quebec & @mcgillu | NLP researcher
Michael Hanna @michaelwhanna
262 Followers 308 Following PhD student at the University of Amsterdam / ILLC, interested in computational linguistics and (mechanistic) interpretability
Zexue He@EMNLP @ZexueHe
256 Followers 102 Following NLP PhD @McAuleyLabUCSD. IBM Ph.D. Fellowship. Previously summer intern @msftresearch. Current intern at @MITIBMLab.
Hyunwoo Kim @hyunw__kim
1K Followers 438 Following Social Reasoning/Commonsense + AI | Postdoc @allen_ai | PhD @SeoulNatlUni
Amanda Bertsch @abertsch72
1K Followers 673 Following PhD student @LTIatCMU / @SCSatCMU, researching text generation + summarization | she/her | also @ abertsch on bsky or https://t.co/L4HBUh0R9f or by email (https://t.co/bsHqwIMFPL)
Hosein Mohebbi @hmohebbi75
245 Followers 341 Following PhD candidate @TilburgU, doing research on interpretability for text and speech. #NLProc
Nishant 🙃 @NishantBalepur
205 Followers 281 Following CS PhD Student. Trying to find that dog in me @UofMaryland. Aligning, Interpreting, and Guiding #LLMs
Shashank Gupta ✈️.. @shashank_bits
398 Followers 1K Following Researcher at @allen_ai (AI2) || Ex-Microsoft || @IllinoisCS graduate || Research on NLP, LLMs, Reasoning, AI4Math, AI4Code, AI4ScientificDiscovery
Vidhisha Balachandran @vidhisha_b
519 Followers 490 Following Senior Researcher @MSFTResearch, PhD from @LTIatCMU, Ex-Intern @allen_ai, @GoogleAI | NLP/AI | she/her
Shivanshu Gupta @shivanshug11
165 Followers 93 Following PhD Candidate at UC Irvine | Previously @asapp @amazon @linkedin @msftresearch @iitdelhi | #NLP & #ML Research
Yasaman Razeghi @yasaman_razeghi
546 Followers 406 Following PhD student in UC Irvine, researching on NLP/ML Student Researcher at Google-Deepmind
Katherine Lee @katherine1ee
6K Followers 931 Following understanding ourselves and our models. senior research scientist @GoogleBrain, @genlawcenter and @CornellCIS, formerly @Princeton @[email protected]
Chan Young Park @chan_young_park
442 Followers 213 Following PhD student @LTIatCMU @uwcse, working on natural language processing and computational social science.
Stanford HAI @StanfordHAI
86K Followers 558 Following The official account of the @Stanford Institute for Human-Centered AI, advancing AI research, education, policy, and practice to improve the human condition.
Emily Chang @emilychangtv
205K Followers 2K Following Host and executive producer of “The Circuit” on @Bloomberg Originals. Author of Brotopia. Proud mama and wife of @jonstull
Nirit Weiss-Blatt, Ph.. @DrTechlash
4K Followers 222 Following Communication Researcher. Author: TECHLASH 📖. Former Visiting Research Fellow @USC. 📝 AI Panic Newsletter. @techdirt @TheDailyBeast @BigThink @TechPolicyPress
Kara Swisher @karaswisher
1.5M Followers 2K Following “Vitriolic” and now “shrill”media lady, though dogs can hear me loud and clear
Weiyan Shi @shi_weiyan
3K Followers 683 Following Postdoc @StanfordNLP, incoming assistant professor @Northeastern, PhD @Columbia| Prev Intern @MetaAI |Co-created CICERO | persuasive chatbots + privacy #nlproc
SoCal NLP Symposium @socalnlp
207 Followers 72 Following ☀️🏝️Annual symposium with students and faculty to promote NLP research in the (Southern) California region 👩💻 #SoCalNLP2023 🔜 @ucla, posts by @BrihiJ
Stephanie Chan @scychan_brains
3K Followers 2K Following Senior Research Scientist at DeepMind. Artificial and biological brains 🤖 🧠 Views are my own
@srush_nlp Agree with the post that there is a distinction (and often implicit conflation) of behavioral and mechanistic induction heads. Having a behavior definition seems more natural to me, followed by specific computational implementations of that def (eg on a transformer) 🧵
@lambdaviking not sure why I care, it just seems crazy that this seems to be the most important idea in interpretability, yet I have no idea what it means.
At this point I think I'm just going to use the @lambdaviking bat signal 🔦. Will, have you thought about how either of these definitions formalize? x.com/srush_nlp/stat…
I asked a basic question earlier about what an "Induction Head" was and whether a non-Transformer could have one. The clear answer is no / yes, as Induction Heads means two orthogonal things. lesswrong.com/posts/nJqftaco…
@BoseShamik @naaclmeeting @naacl i’m reading this as paper needs full registration ($750), but can be presented by a student ($250).
LLMs are often said to "hallucinate", "confabulate", or produce untruthful responses, which led to much work trying to mitigate such behavior. But what does it mean for an LM to hallucinate? And how can we effectively intervene in model internals to combat hallucinations?
There is a really nice community of researchers developing transformer alternatives. Want to highlight these impressive folks. Simran Arora (@simran_s_arora), Chunting Zhou (@violet_zct), Dan Fu (@realDanFu), and Songlin Yang (@SonglinYang4)
Our work rethinking LLMs for health equity through a case study of maternal health was accepted to FAccT 2024 in Rio de Janeiro! 🇧🇷
Maria (@maria_antoniak) is a rock-star researcher, and it was a dream to work with her, @arnaik19, Carla S. Alvarado, and @lucyluwang on this project rethinking LLMs for maternal health -- with lessons for other medical contexts
Thank you so much @CAIS_USC! It was wonderful meeting students and faculty who are excited about AI for social good 🌎
Congratulations to the ShowCAIS Best Student Poster Award winners Jaspreet Ranjit, David Chu, Priyanka Dey, and Caroline Johnston!!! We are so proud of you 🥳✌️ Check out their abstracts: sites.google.com/usc.edu/showca… @Carol_Marge_J @jaspreetranjit_ @USCViterbi @uscsocialwork
I'll be attending #FAccT2024! :-) Let me know if you want to chat! #NLProc #gender
Some personal updates: I joined OpenAI a few months ago, working on all things robustness/safety/privacy. Also, we are working to publish more of our safety work. See my first project here below, where we make initial progress on prompt injections and other attacks!
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details: arxiv.org/abs/2404.13208
Personally, I believe in data, but it would be more fun if I could be proven wrong by architecture, optimization, and other learning algorithm researchers.
The dataset is everything. Great read: nonint.com/2023/06/10/the…
Excited to give a talk tomorrow at @USC_ISI! Open to everyone, but you need to email [email protected] ahead of time to be admitted.
We had a small party to celebrate Llama-3 yesterday in Paris! The entire LLM OSS community joined us with @huggingface, @kyutai_labs, @GoogleDeepMind (Gemma), @cohere As someone said: better that the building remains safe, or ciao the open source for AI 😆
Walking around the OpenAI office and these signs are everywhere
Super excited to talk at UBC next week and catch up with nlp people and amazing @VeredShwartz
We are excited to host @faeze_brh from @ai2_mosaic and @UW for a talk titled "Creativity, Constrained Reasoning, and Problem-Solving". Join us on Monday Apr 29 at 11 am at ICICS 146! @UBCLangScis @CAIDA_UBC
🆕I'm excited to share that I'll start my Ph.D. at @UChicago within @UChicagoCI under Prof. @MinaLee__ 's guidance and Prof. Ari Holtzman (@universeinanegg)'s co-advise! I hope to bring my LLM generation and evaluation works to a more human-centered and interactive stage.
PhDone!!!! 👨🎓 08/2019-04/2024 What a journey 🥳🚞 I especially feel lucky to share this once-in-a-life-time moment with people I love ❤️ . And seeing my passion-driven research efforts being acknowledged by researchers I deeply admire 🌞!! Special thanks to my awesome committee…
Trends for United States
You might like
