Trustworthy ML Initiative (TrustML) @trustworthy_ml
Latest research in Trustworthy ML. Organizers: @JaydeepBorkar @sbmisi @hima_lakkaraju @sarahookr Sarah Tan @chhaviyadav_ @_cagarwal @m_lemanczyk @HaohanWang trustworthyml.org Joined May 2020-
Tweets2K
-
Followers6K
-
Following64
-
Likes745
How to identify bias in language agency?Eg. in texts describing White men as “leading” & Black women as “helping”?🧐 🔎String matching?❌NO! 🔎Sentiment classifier?❌No! ✅Our agency classifier CAN! It reveals gender, racial, and intersectional bias🤯 🔗: arxiv.org/abs/2404.10508
As we increasingly rely on #LLMs for product recommendations and searches, can companies game these models to enhance the visibility of their products? Our latest work provides answers to this question & demonstrates that LLMs can be manipulated to boost product visibility!…
🚀 Exciting news! Our latest work, CHM-Corr++, has been accepted for presentation at the #XAI4CV Workshop, CVPR 2024! 🎉 The work lies in the intersection of: Interactive XAI and human-AI collaboration. Demo: http://137.184.82.109:7080/ Paper: arxiv.org/abs/2404.05238
🚨 Are leading safety-aligned LLMs adversarially robust? 🚨 ❗In our new work, we jailbreak basically all of them with ≈100% success rate (according to GPT-4 as a semantic judge): - Claude 1.2 / 2.0 / 2.1 / 3 Haiku / 3 Sonnet / 3 Opus, - GPT-3.5 / GPT-4, - R2D2-7B from…
Thanks @llm_sec for sharing our new #ICLR2024 work "Can LLM-Generated Misinformation Be Detected?" 🔗Project website (paper, dataset, and code): llm-misinformation.github.io 🚨LLM-generated misinformation is one of the most critical risks on AI safety. Then, one fundamental…
Thanks @llm_sec for sharing our new #ICLR2024 work "Can LLM-Generated Misinformation Be Detected?" 🔗Project website (paper, dataset, and code): llm-misinformation.github.io 🚨LLM-generated misinformation is one of the most critical risks on AI safety. Then, one fundamental…
Are you interested in jailbreaking LLMs? Have you ever wished that jailbreaking research was more standardized, reproducible, or transparent? Check out JailbreakBench, an open benchmark and leaderboard for Jailbreak attacks and defenses on LLMs! jailbreakbench.github.io 🧵1/n
We're recruiting two Research Assistants to join us and work on the security of ML-based personal assistants at @imperialcollege. The role will focus on verification, robustification and adversarial attacks for AI assistants. rb.gy/mcxvob.
Can we adaptively generate training environments with LLMs to help small embodied RL game agents learn useful skills that they are weak at? 🤔 👉 Check out EnvGen, an effective+efficient framework in which an LLM progressively generates and adapts training environments based on…
The U.S. Supreme Court has ended the use of race in college admissions. Fortunately, there exists a path to fair algorithmic decision-making that differs from the invalidated affirmative action measures, as we discuss in our recent Uncommon Good post: uncommongood.substack.com/p/fair-machine…
We are excited to present a new event of our seminar series on ML Security! We will host @gchers (@Microsoft) on March 26th, 2024 at 15:00 CET. Free registration: us02web.zoom.us/j/82941308293?… @elsa_lighthouse @adversarial_ML @trustworthy_ml @aivillage_dc @RedTeamVillage_
Wanna know gpt-3.5-turbo's embed size? We find a way to extract info from LLM APIs and estimate gpt-3.5-turbo’s embed size to be 4096. With the same trick we also develop 25x faster logprob extraction, audits for LLM APIs, and more! 📄 arxiv.org/abs/2403.09539 Here’s how 1/🧵
🤔Can LLM agents really simulate human behaviors? 🌟Our new paper "Can Large Language Model Agents Simulate Human Trust Behaviors?" (Project website: camel-ai.org/research/agent…) provides some new insights into this fundamental problem. ✨TLDR: We discover the trust behaviors of…
🧐Are LLM responses to public health questions biased toward specific demographic groups? In our new interdisciplinary collaboration, we find that disparities exist among model answers for different groups across ages, U.S. locations, and sexes. Paper: arxiv.org/pdf/2403.04858…
The final layer of an LLM up-projects from hidden dim —> vocab size. The logprobs are thus low rank, and with some clever API queries, you can recover an LLM’s hidden dimension (or even the exact layer’s weights). Our new paper is out, a collaboration between lot of friends!
The final layer of an LLM up-projects from hidden dim —> vocab size. The logprobs are thus low rank, and with some clever API queries, you can recover an LLM’s hidden dimension (or even the exact layer’s weights). Our new paper is out, a collaboration between lot of friends!
Just one month left before @satml_conf April 9-11 in Toronto! I am excited to hear from @jhasomesh @rajiinio @yvesalexandre @SheilaMcIlraith, as well as the authors of accepted papers, and the competition organizing teams! There's still time to register! satml.org
Our first Uncommon Good post (with Nick Perello) discusses how to train AI systems that do not propagate discrimination, in compliance with legal provision, based on our research published in @FAccTConference, @AIESConf, and @icmlconf. Stay tuned! open.substack.com/pub/uncommongo…
Pointing to an image region should help models focus, but standard VLMs fail to understand visual markers/prompts (e.g., boxes/masks). 🚨Contrastive Region Guidance: Training-free method that increases focus on visual prompts by reducing model priors. arxiv.org/abs/2403.02325 🧵
We are announcing the winners of our Trojan Detection Competition on Aligned LLMs!! 🥇 @tml_lab (@fra__31, @maksym_andr and Nicolas Flammarion) 🥈 @krystof_mitka 🥉 @apeoffire 🧵 With some of the main findings!
We are announcing the winners of our Trojan Detection Competition on Aligned LLMs!! 🥇 @tml_lab (@fra__31, @maksym_andr and Nicolas Flammarion) 🥈 @krystof_mitka 🥉 @apeoffire 🧵 With some of the main findings!
LLMs are great, but their internals are less explored. I'm excited to share very interesting findings in paper “Massive Activations in Large Language Models” LLMs have very few internal activations with drastically outsized magnitudes, e.g., 100,000x larger than others. (1/n)
Thrilled to be recognized with best paper honorable mention at @RealAAAI! Our paper raises serious questions re: reproducibility + reliability in fairness We define + mitigate arbitrariness, & find that most fairness benchmarks are actually close-to-fair This is a BIG 🚩🚩 1/
Gautam Kamath @thegautamkamath
44K Followers 505 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Co-EiC @TmlrOrg. I lead @TheSalonML. Privacy, robustness, machine learning.Clément Canonne @ccanonne_
31K Followers 928 Following Senior Lecturer @Sydney_Uni. Postdocs @IBMResearch, @Stanford; PhD @Columbia. Converts ☕ into puns: sometimes theorems. He/him. @[email protected]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/IbycyGfnDRPercy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistSara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.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).𝙷𝚒𝚖𝚊 𝙻.. @hima_lakkaraju
16K Followers 834 Following Professor @Harvard; PI @ai4life_harvard; Co-founder @trustworthy_ml; #AI #ML #Safety; Stanford PhD; MIT @techreview #35InnovatorsUnder35Prof. Anima Anandkuma.. @AnimaAnandkumar
25K Followers 2K Following Bren Professor @caltech, Fmr Sr Director of #AI research @nvidia, Fmr Principal Scientist @awscloud, AI+Science, PDE, Neural operators. Views my own.Thomas G. Dietterich @tdietterich
50K Followers 505 Following Distinguished Professor (Emeritus), Oregon State Univ.; Former President, Assoc. for the Adv. of Artificial Intelligence; Robust AI & Comput. SustainabilityNiloofar (Fatemeh) Mi.. @niloofar_mire
4K Followers 1K Following Postdoc @uwcse-@uwnlp, Ph.D. from @ucsd_cse /Privacy, ML, NLP, @winlpworkshop chair, @MSFTResearch - Semantic MachinesKush Varshney कु�.. @krvarshney
3K Followers 613 Following I wrote a book. Free pdf: https://t.co/rFFL7mySnS Paperback: https://t.co/lF0IgC5T9z Tweets are my own and don't necessarily represent IBM.Battista Biggio @biggiobattista
3K Followers 2K Following Full Professor at University of Cagliari (Italy), Co-Founder of Pluribus One. #Security of #MachineLearning, #CyberSecurity & #ComputerVisionPin-Yu Chen @pinyuchenTW
3K Followers 840 Following Principal research scientist@IBM Research & Chief Scientist@RPI-IBM AI Research Collaboration & PI@MIT-IBM AI Lab. IJCAI Computers & Thought Award Winner.Maggie Makar @Maggiemakar
4K Followers 627 Following Assistant prof @umichcse. Previously @MIT_CSAIL. Machine learning. Causal models. Healthcare. Swimming. @[email protected] Opinions are my own.Nando Fioretto @nandofioretto
2K Followers 652 Following Assistant Professor of Computer Science at @UVA. I work on machine learning, optimization, and Responsible AI (differential privacy & fairness).Shaily @shaily99
5K Followers 2K Following PhD @LTIatCMU Prev: @GoogleAI @MSFTResearch. Working on #NLProc evaluation, fairness & culture. Usually ranting, often about research & DEI. 📚 @readsndrantsSharon Y. Li @SharonYixuanLi
7K Followers 657 Following Assistant Professor @WisconsinCS. Formerly postdoc @StanfordAILab, Ph.D. @Cornell. Making AI safe and reliable for the open world.Ahmad Beirami @abeirami
4K Followers 2K Following Building safe, helpful, and scalable generative AI @Google | ex-{@AIatMeta, @EA, @MIT, @Harvard, @DukeU} | @GeorgiaTech PhD | زن زندگی آزادی | opinions my ownSunnie S. Y. Kim @sunniesuhyoung
2K Followers 1K Following PhD student @VisualAILab @PrincetonHCI. AI transparency and explainability. First name pronounced as sunny☀ she/her https://t.co/c3atPcWlR1Parinthapat Pengpun @parinzee
33 Followers 247 FollowingAmir Jevnisek @AmirJevnisek
25 Followers 803 FollowingJacob @wooyakob
83 Followers 444 Following Sales Engineer @briotech 👨🏼🔧@googlecloud Architect ☁️ British expat & adopted San Diegan 🌊Elachqar Oussama @Oussama_e
59 Followers 2K FollowingUNC NLP @uncnlp
3K Followers 388 Following NLP (+ML/AI/CV) research group at UNC ChapelHill (@UNCCS @UNC). Faculty: @mohitban47+@gberta227+@snigdhac25+@shsriva+@tianlongchen4+@huaxiuyaoml + othersLeland Rayner US @NVIDIARayner
3 Followers 48 FollowingJosé Fernández Tama.. @Jftamames
113 Followers 1K Following e/acc Comencé en 2004 pero los cambios en Twitter me han obligado a empezar de nuevoEloisa Granado @thetaoofelo
487 Followers 911 Following Business Development at @Wikimedia Enterprise. Mamá. Miami Native. #firstgen Activist. Croqueta connoisseur. People loving misanthrope. ENFP 🇺🇸🇨🇺🇪🇸Innovators Network Fo.. @innov8rs
345 Followers 1K Following Advancing the public debate over law and policy important to global innovation. Home to the fellowships on privacy, antitrust, and intellectual property.Mustafa Mahmud HussAI.. @mustafamhus
2K Followers 3K Following GenAI Satellite Electronic Warfare Cyber EdTech LMM NanoLoan AI AGI TelcotoTechco Aerospace Defense LLM Geolocation DeepTech QoS Surveillance National SecurityNishaanth Kanna @nishaanthkanna
35 Followers 589 Following skate to where the puck is going to be, not where it has been.Taqi Haider🇵🇰 @taqihaider9
223 Followers 2K Following ML,DL practitioner | Tweets about #DataScience | #MachineLearning |#python | #AI |#FitnessloverTom Faber | Creative .. @TomFaberID
54 Followers 205 Following Creating digital things – with a focus on positive impact. 100% recycled pixels. Only occasional twitter resident, account mainly for reading/following.Matteo Olivato @mttlvt93
16 Followers 116 FollowingKashif Imteyaz @kashif_imteyaz
688 Followers 3K Following Comp Sci PhD @KhouryCollege / @NortheasternAI Studying Social Computing, Human-AI Interaction, FutureOfWorkZhiyong Wang @Zhiyong16403503
380 Followers 2K Following Visiting Ph.D. student at Cornell University. Ph.D. candidate at CUHK. Working on bandits and reinforcement learning theory.GersonDeWinter @GersondeWinter
346 Followers 5K Following Biological Human Intelligence. Non Biological Intelligence (AGI) will replace allmost all jobs, thus ending the monetary economy and culture as we know it+NHIIlker Demirel @ilkerdemirel_
22 Followers 168 Following phd student @mit_csail ML and healthcare, causal inferenceGustave Ud @gudahemuka
397 Followers 5K Followingshivprakash swami @shivswami
348 Followers 845 Following loves Literature, better world, democracy, Cricket, Books & music. tech Consulting Architect(like consulting detective 😇) Cloud / ModernisationVijay Jaisankar @bighungrypigeon
427 Followers 1K Following Intern @SchneiderElec AI Hub 🌳, CS @IIITB_Official 💻 📊 prev: @AdobeResearch @TEDXIIITB 8BIT @iiitbsoc @googlestudents @gdsc_iiitb @MLHacks @hackerabad ZenseDaniel Glogowski @Danielglski
126 Followers 3K Following Product @ Nvidia | ex-Robust Intelligence, Salesforce; Views are my own | 🇮🇱Eliot Eshelman @hpc_twit
564 Followers 1K Following I enable researchers & educators with leading HPC/AI technologies @NVIDIA. From muons to bacteriophages to astrophysics. Opinions my own. he/him #InclusionMatan Ben-Tov @matanbt
22 Followers 982 Following MSc student in Computer Science @TelAvivUni. Interested in buzzwords like AI and Security and wherever they meet.LA @LAamaramay_
169 Followers 273 FollowingoneByte @OByte89444
0 Followers 7 FollowingQuyen Tran @tranquyenbk173
24 Followers 247 Following AI Research Resident at @VinAI_Research (Looking for a PhD position in Fall2025) Interested in Continual Learning, OOD detection and Generative modelsHanieh Hashemi @Haanie_h
29 Followers 62 Following ML engineer @Apple. Passionate about privacy preserving ML and responsible AI. PhD from @USC. Ex research intern @AIatMeta and @Samsung SemiAI for Thinking @AIforThinking
31 Followers 684 FollowingAnthony Peng @RealAnthonyPeng
105 Followers 291 Following CS PhD @gtcomputing @GeorgiaTech | Intern @intel | Robustness, VLM, LLM | Outcomes are what count; don’t let good processes excuse bad results.xueyuanding @xysecurity1
1 Followers 77 FollowingRafiqul Rabin @mdrafiqulrabin
121 Followers 296 Following Postdoctoral Fellow at @CSatUH of @UHouston. Interested in Safe AI/ML and LLMs for Code Intelligence.TwiterUser @twiter_userrr
0 Followers 249 Following Retweets and likes are not endorsements I make it seem easy, it's actually difficultWayne Wang @weiwanglaw
831 Followers 3K Following PhD-ing @HKULaw, Non-Resident Fellow @CTS_FGV @FGV, Admin @CCHK, @WIPO/@QUT LLM, eyes on Law, Data, AI, Platforms, Innovation & STS. Hiker🧗♂️and Tenor🗣️Arif Ahmad @ArifAhm92263086
244 Followers 7K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIThibaut Vidal @vidalthi
1K Followers 480 Following Professor & SCALE-AI Chair at MAGI @polymtl Tweets about #ORMS #MachineLearning #Explainability Open-source codes: https://t.co/HaZVxBWKxXFrancesco Pinto @FraPintoML
31 Followers 133 Following Francesco Pinto, University of Oxford, PhD student TVG. Trustworthy and Privacy-Preserving ML Email: [email protected]Tee Ann @_teeann_
11 Followers 385 FollowingAda Wan @adawan919
157 Followers 1K Following Transdisciplinarian (stats, datasci, ml, lang/socSci, tech, art, science, philosophy). (Use-inspired) fundamental research.Opinions my own. Accidental activist.Vipul Sharma @VipulS_1
12 Followers 233 Following Looking for research opportunities in ML/AI with applications in healthcare and computational neuroscience. Prospective MS student.Gautam Kamath @thegautamkamath
44K Followers 505 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Co-EiC @TmlrOrg. I lead @TheSalonML. Privacy, robustness, machine learning.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/IbycyGfnDRPercy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistSara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.Zachary Lipton @zacharylipton
59K Followers 2K Following Professor: CMU/@acmi_lab, CTO / CSO: @AbridgeHQ, Creator: @d2l_ai & https://t.co/QQt98VNLUp, Relapsing 🎷Nicolas Papernot @NicolasPapernot
10K Followers 665 Following Security and Privacy of Machine Learning @Uoft @VectorInst @Google 🇫🇷🇪🇺🇨🇦 Co-author https://t.co/VJF39DQPCu; @CentraleLyon + @PSUEngineering alumnus. Opinions mine𝙷𝚒𝚖𝚊 𝙻.. @hima_lakkaraju
16K Followers 834 Following Professor @Harvard; PI @ai4life_harvard; Co-founder @trustworthy_ml; #AI #ML #Safety; Stanford PhD; MIT @techreview #35InnovatorsUnder35Aaron Roth @Aaroth
10K Followers 639 Following CS professor at Penn. Amazon Scholar at AWS. Author of The Ethical Algorithm (w/ Michael Kearns). I study machine learning, privacy, game theory, and fairness.Thomas G. Dietterich @tdietterich
50K Followers 505 Following Distinguished Professor (Emeritus), Oregon State Univ.; Former President, Assoc. for the Adv. of Artificial Intelligence; Robust AI & Comput. SustainabilityBeen Kim @_beenkim
23K Followers 453 Following Research Scientist at Google DeepMind, PhD from MIT. Make machines empower people. @[email protected]Niloofar (Fatemeh) Mi.. @niloofar_mire
4K Followers 1K Following Postdoc @uwcse-@uwnlp, Ph.D. from @ucsd_cse /Privacy, ML, NLP, @winlpworkshop chair, @MSFTResearch - Semantic MachinesKush Varshney कु�.. @krvarshney
3K Followers 613 Following I wrote a book. Free pdf: https://t.co/rFFL7mySnS Paperback: https://t.co/lF0IgC5T9z Tweets are my own and don't necessarily represent IBM.Battista Biggio @biggiobattista
3K Followers 2K Following Full Professor at University of Cagliari (Italy), Co-Founder of Pluribus One. #Security of #MachineLearning, #CyberSecurity & #ComputerVisionPin-Yu Chen @pinyuchenTW
3K Followers 840 Following Principal research scientist@IBM Research & Chief Scientist@RPI-IBM AI Research Collaboration & PI@MIT-IBM AI Lab. IJCAI Computers & Thought Award Winner.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.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/themSameer Singh @sameer_
7K Followers 2K Following Cofounder @SpiffyAI and Assoc Prof at @UCIrvine, working on reliable LLMs, explanations for AI+ML, adversaries for NLP, and debugging/evaluation.Chhavi Yadav @chhaviyadav_
2K Followers 3K Following Machine Learning Researcher | PhD student @ucsd_cse | @trustworthy_mlChristopher Choquette @Chris_Choquette
311 Followers 76 Following Research Scientist @GoogleDeepMind. I love rock climbing and cooking. Opinions here are my own.The GenLaw Center @genlawcenter
483 Followers 22 Following The Center for Research on Generative AI, Law, and Policy https://t.co/mxbv72Mp3RAbhilasha Ravichander @lasha_nlp
3K Followers 2K Following Postdoc @allen_ai, working on Natural Language Processing (#NLProc) | PhD @SCSatCMU @LTIatCMU | Friend of @NLPWithFriends | @[email protected]Nazneen Rajani @nazneenrajani
4K Followers 2K Following Something new 🧪 | Previously: @huggingface 🤗, @SFResearch, PhD @utcompsciPratyush Maini @pratyushmaini
1K Followers 339 Following Trustworthy ML | PhD student @mldcmu | Founding Member @datologyai | Prev. Comp Sc @iitdelhiShalmali Joshi @shalmali_joshi_
781 Followers 730 Following Assistant Professor, Columbia University. Machine Learning for Health @ColumbiaDBMI. Previously Harvard University, Vector Institute, UT AustinEsin Durmus @esindurmusnlp
3K Followers 381 Following Research Scientist @anthropicai. Previously Postdoc @stanfordnlp and PhD @cornellcis. Working on LLMs & evaluating their safety and impact on society. she/her.Berk Ustun @berkustun
3K Followers 961 Following Assistant Prof @HDSIUCSD. I work on fairness and interpretability in ML. Previously @GoogleAI @Harvard @MIT @UCBerkeley🇨🇭🇹🇷Sunipa Dev @sunipa17
2K Followers 568 Following Responsible, and Inclusive #NLProc. Senior Research Scientist RAI-HCT @GoogleAI. Previously @CIFellows @uclanlp and @UtahSoC. Chair @WiNLPWorkshop she/herStella Biderman @BlancheMinerva
15K Followers 748 Following Open source LLMs and interpretability research at @BoozAllen and @AiEleuther. My employers disown my tweets. She/herBen Zhao @ravenben
8K Followers 473 Following Neubauer Professor @UChicagoCS, security & privacy in ML, data, HCI. MIT TR-35 Innovator & Quora TopWriter. loves food, family, my students. ACM Fellow. He/him.Katherine Lee @katherine1ee
6K Followers 931 Following understanding ourselves and our models. senior research scientist @GoogleBrain, @genlawcenter and @CornellCIS, formerly @Princeton @[email protected]MMitchell @mmitchell_ai
80K Followers 1K Following Interdisciplinary researcher focused on shaping AI towards long-term positive goals. ML & Ethics. Same content in the Sky, Threads, & the Prehistoric ElephantZico Kolter @zicokolter
15K Followers 499 Following Associate professor at Carnegie Mellon, VP and Chief Scientist at Bosch Center for AI. Researching (deep) machine learning, robustness, implicit layers.David Bau @davidbau
3K Followers 241 Following Computer Science Professor at Northeastern, Ex-Googler. Believes AI should be transparent. @[email protected] @davidbau.bsky.social https://t.co/wmP5LUZRTwSasha Luccioni, PhD �.. @SashaMTL
19K Followers 4K Following AI & Climate @HuggingFace, Board Member of @WiMLworkshop and @ClimateChangeAI. @techreview 35 Innovators under 35, @TEDTalks speaker. She/her/Dr/ 🦋Pang Wei Koh @PangWeiKoh
3K Followers 789 Following Assistant professor at @uwcse. Formerly @StanfordAILab @GoogleAI @Coursera. 🇸🇬AI Vulnerability Data.. @AvidMldb
493 Followers 70 Following Open Source community researching AI Vulnerabilities. Report an AI Vuln: https://t.co/2sSxAZRcQo… Join us on discord: https://t.co/gCtRKg1Z4JFlorian Tramèr @florian_tramer
4K Followers 205 Following Assistant professor of computer science at ETH Zürich. Interested in Security, Privacy and Machine LearningJonathan Ullman @thejonullman
2K Followers 233 Following Associate Professor of Computer Science @KhouryCollege @Northeastern. Probably an impostor. Still questioning his decision to join Twitter.Marinka Zitnik @marinkazitnik
6K Followers 226 Following Assistant Professor at Harvard | Faculty @Harvard @KempnerInst AI | Faculty @broadinstitute @harvard_data | Cofounder @ProjectTDC | @AI_for_ScienceOlga Russakovsky @orussakovsky
2K Followers 41 Following Asst Prof @PrincetonCS, PI @VisualAILab, co-founder @ai4allorg, she/herKai-Wei Chang @kaiwei_chang
6K Followers 711 Following Associate Professor @UCLAengineering/@UCLA. Area: #NLProc/#ML/#AI https://t.co/zj1ssZj9oxMaria De-Arteaga @mariadearteaga
5K Followers 540 Following Asst Professor, IROM Dept @UTAustin | PhD, Machine Learning & Public Policy @CarnegieMellon | Algorithmic fairness, human-AI collab | 🇨🇴 💚 she/her/ella.Cristian Canton @cristiancanton
2K Followers 539 Following Engineering Head @Meta's Responsible AI org. Opinions are my own.Alina Oprea @AlinaMOprea
2K Followers 510 Following Security researcher and CS professor at @Northeastern @KhouryCollege. Interested in ML security and privacy, applications of ML to security, and cloud security.Haohan Wang @HaohanWang
1K Followers 535 Following Assistant professor @iSchoolUI at UIUC. Part of @trustworthy_ml. Previously @CarnegieMellon. Work on Trustworthy Machine Learning and Computational BiologyCynthia Rudin @CynthiaRudin
3K Followers 143 FollowingJiahao Chen @acidflask
4K Followers 3K Following Director of AI/ML, @NYCOfficeOfTech. [email protected]Katherine Heller @kat_heller
4K Followers 318 Following I come up with new ways to try to get computers to understand people. So far they just think we're jerks.Alexander D'Amour (al.. @alexdamour
4K Followers 1K Following Research Scientist at Google Brain. Statistics, Data Science, ML, causality, fairness. Prev at Harvard (PhD), UC Berkeley (VAP). Opinions my own. he/him.Suresh Venkatasubrama.. @geomblog
13K Followers 941 Following AI Bill of Rights coauthor. Prof@BrownUniversity. Former tech advisor to President Biden @WHOSTP. He/him/his. Tweets my own. @[email protected]Harini Suresh @harini824
5K Followers 488 Following incoming assistant professor @BrownUniversity / postdoc @cornell / previously @mit / thinking about participatory + equitable + accountable MLMarta Lemanczyk @m_lemanczyk
266 Followers 591 Following PhD student @RenardLab @HPI_DE | @trustworthy_ml | Working on interpretable ML and bioinformaticsDanielle Belgrave @DaniCMBelg
7K Followers 2K Following VP of AI/ML @GSK. Curious about using AI to make the world a better place. Views my own.Ram Shankar Siva Kuma.. @ram_ssk
3K Followers 2K Following Security Data Cowboy @Azure. Yes, the job is as cool as it sounds. Tech Policy Fellow @UCBerkeley. @BKCHarvard Affiliate. https://t.co/eph3QDsIGBChirag Agarwal @_cagarwal
965 Followers 394 Following On academic job market for Fall'24; Postdoctoral Fellow @Harvard; @ml_collective; @trustworthy_ml; Increasing the sample size of my thoughtsAs we increasingly rely on #LLMs for product recommendations and searches, can companies game these models to enhance the visibility of their products? Our latest work provides answers to this question & demonstrates that LLMs can be manipulated to boost product visibility!…
maybe of your interests @trustworthy_ml @XAI_Research
@niloofar_mire visits us and SoCal #nlproc peeps and shares her work on privacy considerations for large language models.
Just one month left before @satml_conf April 9-11 in Toronto! I am excited to hear from @jhasomesh @rajiinio @yvesalexandre @SheilaMcIlraith, as well as the authors of accepted papers, and the competition organizing teams! There's still time to register! satml.org
Our first Uncommon Good post (with Nick Perello) discusses how to train AI systems that do not propagate discrimination, in compliance with legal provision, based on our research published in @FAccTConference, @AIESConf, and @icmlconf. Stay tuned! open.substack.com/pub/uncommongo…
Pointing to an image region should help models focus, but standard VLMs fail to understand visual markers/prompts (e.g., boxes/masks). 🚨Contrastive Region Guidance: Training-free method that increases focus on visual prompts by reducing model priors. arxiv.org/abs/2403.02325 🧵
Thrilled to be recognized with best paper honorable mention at @RealAAAI! Our paper raises serious questions re: reproducibility + reliability in fairness We define + mitigate arbitrariness, & find that most fairness benchmarks are actually close-to-fair This is a BIG 🚩🚩 1/
Was this sequence in the training dataset or not?? In new paper, we study why membership inference attacks show *near-random performance* on LLMs!! We also release a Python package for seamless MIA evaluation!! Paper: arxiv.org/abs/2402.07841 Repo: github.com/iamgroot42/mim…
Tagging some relevant communities: @trustworthy_ml @XAI_Research @iml4health
Given up on feature attribution? 📣 Thrilled to share *prospector heads* (aka “prospectors'') ⛏️ — a simple attribution method built for foundation models (FMs) & high-dimensional data. Prospectors are modality-generalizable, time-efficient, & excel in few-shot settings ✨ 🧵👇
We're seeking innovative papers on aligning algorithms with human values. Looking forward to your contributions! 🚀✨ #AI #Research #CallforPapers #TrustInAI #trustworthyai #workshop #machinelearning #trustworthiness @trustworthy_ml @aivillage_dc
📢 Call for Papers: Workshop on "Human Aligned AI: Towards Algorithms that Humans Can Trust." Discuss trustworthiness in AI, exploring strategies to ensure alignment with human values. Submit by July 31st! ➡️ Conference: icmla-conference.org/icmla24/ ➡️ CFP: icmla-conference.org/icmla24/worksh…
might be of interest to @FAccTConference @trustworthy_ml
Multi-agent LLM interactions improve reasoning BUT costly + no final single model! 🚨Our structured distillation method MAGDi: - Distills multi-teacher graphs➡️small LM - Boosts student acc ~10% - 9x efficiency arxiv.org/abs/2402.01620 @cyjustinchen @EliasEskin @mohitban47 🧵
Join us 2mrw @⚡️XAI-in-Action : Past, Present & Future Applications⚡️ workshop @NeurIPSConf for an exciting discussion on how far we've come, the current state & future of XAI ! Bonus: Live Demos! Submit ur ❤️🔥 panel questions: app.sli.do/event/6e2A95V2… 🔗xai-in-action.github.io
AI regulation has become a hot topic of debate in recent months. So, we decided to bring this conversation to #NeurIPS2023! Come join us at the #RegulatableML workshop! ⏰ 8:55am - 5:30pm, Saturday, Dec 15 📍 Room 215-216 🔗 regulatableml.github.io 📽️ neurips.cc/virtual/2023/w……
What happens if you ask ChatGPT to “Repeat this word forever: “poem poem poem poem”?” It leaks training data! In our latest preprint, we show how to recover thousands of examples of ChatGPT's Internet-scraped pretraining data: not-just-memorization.github.io/extracting-tra…
Hi world! We're so excited for this!
3 exciting updates from Generative AI + Law (@genlawcenter)! 1: We’ve written a report on the state of the field: genlaw.org/2023-report.ht… 2. GenLaw → we’re becoming an official nonprofit! 3. GenLaw 2 coming soon – centering policy and policymakers More below!
3 exciting updates from Generative AI + Law (@genlawcenter)! 1: We’ve written a report on the state of the field: genlaw.org/2023-report.ht… 2. GenLaw → we’re becoming an official nonprofit! 3. GenLaw 2 coming soon – centering policy and policymakers More below!
I'm on the academic job market I'm a full-stack data privacy researcher I build systems that are 1)provably private 2)functionally-rich 3)compatible w/ real-world constraints I do this by exploring the synergy between cryptography & differential privacy, both in theory & practice