Anna Hedström @anna_hedstroem
ML PhD student @UMI_Lab_AI at @TUBerlin | evaluation-centric interpretability Joined November 2020-
Tweets92
-
Followers281
-
Following257
-
Likes398
Our paper on finding the right #XAI Method — A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science has been accepted at @AMS_AIES 🎉 Check out the early release: doi.org/10.1175/AIES-D…
Had a wonderful time teaching in Porto last week Many fascinating discussions on the future of XAI Congratulations @INVICTA_School for the brilliant organisation. If you're an AI researcher or PhD student, make sure to apply to next year's school
Had a wonderful time teaching in Porto last week Many fascinating discussions on the future of XAI Congratulations @INVICTA_School for the brilliant organisation. If you're an AI researcher or PhD student, make sure to apply to next year's school
Join us next week as @BommerPhiline and I talk about evaluation-centric interpretability in climate science 🗓️ Feb 21, 7am PT / 4pm CET Sign-up (for free) climatechange.ai/webinars @ClimateChangeAI
Happy to see our work “Sanity Checks Revisited” making it to NeurIPS @XAI_in_Action! Looking forward to connecting with many of you there
Happy to see our work “Sanity Checks Revisited” making it to NeurIPS @XAI_in_Action! Looking forward to connecting with many of you there
Wishing everyone a joyous holiday season filled with warmth, laughter, and all-around great Christmas vibes! 🎄✨
Excited to share our latest #NeurIPS2023 paper "Labeling Neural Representations with Inverse Recognition." (arxiv.org/abs/2311.13594) We present INVERT — new global explanation method that explains neurons with human-understandable concepts they detect! A thread 🧵(1/8)
Exciting news: I'll delivering lectures on Explainable AI at INVICTA's Spring School in AI in March next year. For registration and more info: invicta.inesctec.pt Looking forward to learning together!
Exciting news: I'll delivering lectures on Explainable AI at INVICTA's Spring School in AI in March next year. For registration and more info: invicta.inesctec.pt Looking forward to learning together!
Yihaaaa see you in December #neurips2023
Yihaaaa see you in December #neurips2023
In @SeifertChristin’s talk at XAI^3 worship at #ECAI2023, our Quantus library was named one of the top XAI evaluation libraries! Great job @anna_hedstroem and co-authors!
📣📣📣 @kirill_bykov
👏 Exciting News! 🎉 Our lab is thrilled to welcome Sezer Kutluk as our new Post-doc researcher specializing in Explainable AI. 🤖📊 With his expertise, we're poised to make even greater strides in understanding and interpreting AI models. Welcome to the team, Sezer! 🌟#XAI
Excited to be back at @SFI_VI's brilliant interpretability workshop, hosted by Alba and @MKampffmeyer. Today, I shared findings from our recent TMLR paper: "The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus" openreview.net/pdf?id=j3FK00H…
The AI Department at @FraunhoferHHI is currently looking for a student research assistant (!) Apply here: lnkd.in/eNR3vpM8 Don't miss this golden opportunity to work with @SLapuschkin @WojciechSamek and other great ML researchers
Friends, Subscribers, Fellow Academics, lend me your ears (eyes), A new paper from our group! Congratulations to @anna_hedstroem and @UMI_Lab_AI #XAI #MachineLearning #deeplearning
Friends, Subscribers, Fellow Academics, lend me your ears (eyes), A new paper from our group! Congratulations to @anna_hedstroem and @UMI_Lab_AI #XAI #MachineLearning #deeplearning
Don't forget to check out our Github repo! github.com/annahedstroem/… Paper: openreview.net/pdf?id=j3FK00H…
Don't forget to check out our Github repo! github.com/annahedstroem/… Paper: openreview.net/pdf?id=j3FK00H…
Dream lab
How to evaluate your XAI method?? 👉 Use Quantus (github.com/understandable…) But how do you evaluate the evaluation metrics used for XAI evaluation??🤯 👉 Use MetaQuantus (pypi.org/project/metaqu… published @TmlrPub) #publishedAtTMLR #MetaQuantus #XAI #AI
Thrilled to share that our Meta-Evaluation paper has been accepted for TMLR publication! Available at: openreview.net/forum?id=j3FK0…. Immense gratitude to my collaborators @BommerPhiline @SLapuschkin @Marina_MCV @WojciechSamek + Kristoffer
Thrilled to share that our Meta-Evaluation paper has been accepted for TMLR publication! Available at: openreview.net/forum?id=j3FK0…. Immense gratitude to my collaborators @BommerPhiline @SLapuschkin @Marina_MCV @WojciechSamek + Kristoffer
Marta Marchiori Maner.. @Marta_Marchiori
448 Followers 1K Following PhD Student in AI for Society at @UniPisa w @kdd_lab | Responsible NLP; XAI; Fairness; Abusive Language | Member of @krino_org & @privacynetwork_ | she,herGabriele 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.Chandan Singh @csinva
885 Followers 506 Following Senior researcher @MSFTResearch. Seeking good explanations with machine learning. Likes trees and brains. PhD from @Berkeley_AIpispispist @andrejoandrejo
15 Followers 9 FollowingJake van der Laan @jvanderlaan
329 Followers 617 Following Educator, machine learning guy, skeptic, reader, John Rawls fan.Lobiten @LobitenAI
17 Followers 118 Following Data Scientist working on making model more reliable via interpretable and explainable methods. Subjects : Trustworthy, Causality, XAITrisha Chetani @TrishaChetani
1K Followers 5K Following 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞𝐝 𝐀𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐨𝐧 𝐓𝐞𝐬𝐭𝐞𝐫 𝐜𝐮𝐫𝐫𝐞𝐧𝐭𝐥𝐲 𝐩𝐮𝐫𝐬𝐮𝐢𝐧𝐠 𝐦𝐲 𝐌𝐚𝐬𝐭𝐞𝐫'𝐬 𝐢𝐧 𝐀𝐈/𝐌𝐋 Open for anew opportunityShah Nawaz @Shahnawazgrewal
631 Followers 2K Following Assist. Prof in CV @jkulinz | Former @imec_int, @desy, @IITalk. @Uni_Insubria, @TUeindhoven, @TUBerlin, @EIT_Digital. Tweets r strictly personal opinionThe Artificially Inte.. @theaienterprise
1K Followers 2K Following The Artificially Intelligent Enterprise is a newsletter and online conference for business users adopting artificial intelligence produced by @mrhinkle.Helder Marques @HelderFMarques
85 Followers 1K FollowingAuwal Musa @auwal_musam
163 Followers 939 Following Research Scientist | Analytically minded Leverages expertise in data & analytics to drive cutting-edge solutions. Data & Analytics🔽 https://t.co/oIsqf2jRNBBobby Lancaster @BobbyLancasterX
2K Followers 4K Following Building AI tools to visualize the transformer attention mechanism. Host @DarkestLightPod Founder @Alchemical_AIGustave Ud @gudahemuka
397 Followers 5K FollowingSiyi Wu @ssseawu
3 Followers 40 FollowingHayden So @haydsso
38 Followers 663 Following cs + earth systems @hkust // prev intern @YaleMed // co-host @therecallpod // @uwcint alumPaul F. Jäger @pfjaeger
701 Followers 295 Following Heading the Interactive Machine Learning Research Group @dkfz and @helmholtz_image. Previously @KIT, @mic_dkfz, and @facebookai.Suzanne Stathatos @suzstathatos
825 Followers 2K Following PhD student @Caltech researching computer vision for conservation and biodiversity monitoring 🌎 Prev. SDE @Amazon, @NASAJPL; BA, MS @StanfordTuomas Oikarinen @tuomasoi
62 Followers 147 Following Developing scalable ways to understand neural networks. PhD student at UCSD. https://t.co/aiLkcm9OIDimmanuΕLle @iammteah
177 Followers 753 Following (without (*)) chaos never turns into beauty | discovering structures and exploring complex dynamics ~ applied computer science & digital humanities @UniLeipzigUnbox Research @unboxresearch
750 Followers 648 Following We write articles about AI! https://t.co/YfdaFwMP2d We’re a machine learning research & development company. We find answers in data. Founded by @tylerneylon.Elias Schwalme @EliasSchwalme
713 Followers 704 Following building @lee_ai_avatar - interested in product & humans.Aroosa Ijaz @AroosaIjaz3
509 Followers 1K Following Quantum Computing researcher at LANL, Vector Institute, UWaterlooErfan Hatefi @Erfan_vh
33 Followers 91 Following Research Assistant @FraunhoferHHI - Master's Student @TUBerlin - Deep Learning, XAI, InterpretabilityAFilipa Sequeira @AFilipaSequeira
37 Followers 84 FollowingSnafi @Snafi008
46 Followers 255 FollowingAmir-Hossein Karimi @amirhkarimi_
2K Followers 2K Following 🇮🇷 🇨🇦 👨🏻🏫 Asst Prof of ML @UWaterloo & Faculty Affiliate @VectorInst 🔎 Explainable AI, Human-AI Teams 🧠🤖 ex-{@DeepMind, @GoogleAI, @Meta} CHARM Lab👇Hugo Larochelle @hugo_larochelle
113K Followers 627 Following Google DeepMind researcher, machine learning professor, ex-Twitter Cortex, father of 4, wine/music/comedy enthusiastSimone Azeglio @simoneazeglio
683 Followers 625 Following From Physics to Vision Neuroscience & AI | PhD Candidate @InstVisionParis & @ENS_ULM | Prev @CERN | co-organizer @neur_repsPablo Sánchez @ML_pablosm
346 Followers 494 Following PhD student in Machine Learning at @MPI_IS @SIC_Saar #IMPRSIS. Previously in @uc3m.Nektarios Kalampaliki.. @NKalampalikis
2 Followers 47 FollowingFlorian Mahner @florianmahner
126 Followers 349 Following PhD candidate with @martin_hebart at @MPI_CBS. Interested in artificial and biological vision. Also spent time @DondersInst, @bccn_berlin, @UniOsnabrueck.EdgeAI Geek @edgeaiguy
1K Followers 5K Following Crafting AI solutions for tiny devices. Preparing for AGI world !Laura Waltersdorfer @LaWaltersdorfer
56 Followers 428 Following Praedoc Student @tu_wien and @semsys_research Research Topic: Auditable Semantic Web Machine Learning SystemsSimon Schrodi @SimonSchrodi
71 Followers 127 Following 🎓 PhD student in interpretability @UniFreiburg @CVisionFreiburg 💡 interested in mechanistic interpretability, robustness, AutoML & ML for climate scienceVasilis Gkolemis @givasile1
58 Followers 270 Following Explainable AI | Uncertainty Quantification | PhD Student @ HUA | Research Assistant @ ATHENA RCDr. Total Environment @water_yog
2K Followers 4K Following #Environment #Hydrology #Climate #politics #boating #yogaAnshul Nasery @anshulnasery
316 Followers 1K Following PhD student at @uwcse | Previously Pre-Doctoral Researcher at @GoogleAI, undergrad at @iitbombayx @independent_bet
0 Followers 1K FollowingCatherine Olsson @catherineols
15K Followers 1K Following Hanging out with Claude, improving its behavior, and building tools to support that @AnthropicAI 😁 prev: @open_phil @googlebrain @openai (@microcovid)Anthropic @AnthropicAI
264K Followers 26 Following We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant Claude at https://t.co/aRbQ97uk4d.Stanford AI Lab @StanfordAILab
137K Followers 319 Following The Stanford Artificial Intelligence Laboratory (SAIL), a leading #AI lab since 1963. ⛵️🤖 Emmy-winning video: https://t.co/lV9smZTC1mChandan Singh @csinva
885 Followers 506 Following Senior researcher @MSFTResearch. Seeking good explanations with machine learning. Likes trees and brains. PhD from @Berkeley_AIInt’l Telecommunica.. @ITU
110K Followers 2K Following UN agency for digital tech, connecting the world through #spectrum management, brokering #standards + bridging the #DigitalDivide. Secretary-General: @ITUSecGenEzra Klein @ezraklein
2.6M Followers 1K Following Columnist, @NYTOpinion Author, "Why We're Polarized" Host of "The Ezra Klein Show" podcastYu Meng @yumeng0818
1K Followers 161 Following Asst. Professor @CS_UVA, Past: PhD from @IllinoisCS, visiting researcher @princeton_nlp, Google PhD Fellow. NLP/ML/LLMSholto Douglas @_sholtodouglas
15K Followers 862 Following Scaling Gemini @Deepmind - working towards intelligence too cheap to meterShiv Rao, MD @ShivdevRao
1K Followers 2K Following Building @AbridgeHQ + random musings at intersection of Revenant records, late 90s skateboarding, Vincent Van Duysen, and cardiology.Frank Nielsen @FrnkNlsn
23K Followers 1K Following Machine Learning & AI, Information Sciences & Information Geometry, Distances & Statistical models, HPC. "Geometry defines the architecture of spaces" @SonyCSLEvan Mays @evanon0ping
873 Followers 233 Following preparedness @openai prev @tryrootbeer, InstagramNathan Labenz @labenz
14K Followers 2K Following AI Scout, building text-2-video @Waymark, host of The Cognitive Revolution podcastJenn Wortman Vaughan @jennwvaughan
10K Followers 572 Following Sr Principal Researcher, Microsoft Research, NYC. Machine learning transparency, intelligibility, fairness. WiML co-founder. NeurIPS 2021 Program Co-Chair.Amir-Hossein Karimi @amirhkarimi_
2K Followers 2K Following 🇮🇷 🇨🇦 👨🏻🏫 Asst Prof of ML @UWaterloo & Faculty Affiliate @VectorInst 🔎 Explainable AI, Human-AI Teams 🧠🤖 ex-{@DeepMind, @GoogleAI, @Meta} CHARM Lab👇Mistral AI @MistralAI
91K Followers 0 Following Fast, open-source and secure language models. Join us https://t.co/INALdNGvCPKim Andrea Nicoli @nicoli_kim
247 Followers 270 Following Postdoc Uni Bonn, HISKP 🇩🇪 Prev. @bifoldberlin, @ml_tuberlin ➡️ PhD in Machine Learning ➡️ theoretical physicist Foodie, climber, runner!🧗🏻Lukas Klein @lukas_kln
130 Followers 199 Following PhD Student @DKFZ and @ETH Zürich | Helmholtz Imaging | Working on Knowledge Discovery and Explainable AI.Leshem Choshen 🤖�.. @LChoshen
4K Followers 550 Following 🥇 Collaborative LLMs 🥈 Opinionatedly sharing #ML & #NLP 🥉 Propagating us underdogs we owe science an alternative hype @IBMResearch & @MIT_CSAILAlfredo Canziani @alfcnz
87K Followers 268 Following Musician, math lover, cook, dancer, 🏳️🌈, and an ass prof of Computer Science at New York UniversityAsma Ghandeharioun @ghandeharioun
2K Followers 489 Following Research Scientist @GoogleAI working on ML interpretability & human-centered AI, PhD from @MITChris Olah @ch402
91K Followers 173 Following Reverse engineering neural networks at @AnthropicAI. DMs open! Previously @distillpub, OpenAI Clarity Team, Google Brain. Personal account.Hugo Larochelle @hugo_larochelle
113K Followers 627 Following Google DeepMind researcher, machine learning professor, ex-Twitter Cortex, father of 4, wine/music/comedy enthusiastJohanna Vielhaben @jvielhaben
24 Followers 94 Following PhD student at Fraunhofer HHI in Berlin, working on eXplainable AI, with a MSc in Physics.Keren Gu 🌱👩🏻.. @KerenGu
2K Followers 458 FollowingIda Momennejad @criticalneuro
15K Followers 2K Following Principal Researcher @MSFTResearch. I study memory/planning in brains. I build/evaluate AI. Writing on Memory. Finishing a novel. Cohost https://t.co/rgvLjhBvSHChristin Seifert @cse.. @SeifertChristin
155 Followers 71 Following Artificial Intelligence in medicine, making AI/ML transparent, understandable and trustworthy. Professor at @Uni_MR and @UTwente. She/her.Hanna Wallach (@hanna.. @hannawallach
22K Followers 944 Following Microsoft Research NYC. Fairness, accountability & transparency in AI/ML. NeurIPS & ICML board member, WiML co-founder, sloth enthusiast. She/her.Tiago Filipe Sousa Go.. @GalvesTiago
200 Followers 1K Following PhD Student @feup_porto, Research Assistant @INESCTEC, Visiting PhD Student @MGHMartinos & @qtimlab, Medical xAI Researcher. Opinions are my own.Parshin Shojaee @ParshinShojaee
1K Followers 976 Following PhD student @VT_CS | AI for Science, Math, Code, Reasoning | Intern (incoming) @AdobePedro Neto @Pedro18_Neto
202 Followers 709 Following PhD student at FEUP @ INESC TEC. Working towards explainable AI. Aalto University, Finland and ISEP, PortugalINVICTA School @INVICTA_School
26 Followers 2 Following INVICTA - is a school of artificial intelligence, computer vision and pattern analysisDr. Karen Ullrich @karen_ullrich
4K Followers 563 Following Research scientist at FAIR NY + collab w/ Vector Institute. ❤️ Machine Learning + Information Theory. Previously, PhD at UoAmsterdam, intern at DeepMind + MSRC.🔭 Galileo @rungalileo
524 Followers 116 Following Data quality platform for data science teams working with NLP, Computer Vision and Generative AI.Vikram Chatterji @vikramchatterji
194 Followers 230 Following Co-founder @rungalileo GenAI Development Platform // Prev Product @GoogleAIDeepLearning.AI @DeepLearningAI
221K Followers 30 Following We are an education technology company with the mission to grow and connect the global AI community.Hugging Face @huggingface
347K Followers 189 Following The AI community building the future. https://t.co/VkRPD0VKaZ #BlackLivesMatter #stopasianhateKristof T. Schütt @ktschuett
657 Followers 366 Following Deep learning scientist, amateur quantum chemist, musician, audio engineer. Whatever comes up. Bluesky: @ktschuett.bsky.socialYann Dubois @yanndubs
4K Followers 1K Following PhD student @stanfordAILab | Prev: AI resident @metaai, @vectorinst, @CambridgeMLGFiddler AI @fiddlerlabs
3K Followers 488 Following Build trust into AI with Fiddler - the pioneer in AI Observability. Monitor, explain, analyze, and improve your ML models and AI solutions.Berkeley AI Research @berkeley_ai
150K Followers 190 Following We're graduate students, postdocs, faculty and scientists at the cutting edge of artificial intelligence research.Elizabeth Barnes @BethMayBarnes
664 Followers 201 FollowingZining Zhu @zhuzining
605 Followers 483 Following Incoming assistant Professor @FollowStevens (2024-) Current: PhD candidate at @UofT, @VectorInst Areas: #NLProc #AIArthur @itsArthurAI
2K Followers 603 Following The AI Performance Company, on a mission to make AI better for everyone and build ML technology to drive responsible business results. Tweets written by humans.Princeton PLI @PrincetonPLI
1K Followers 19 Following Princeton University initiative enhancing fundamental understanding of AI, enabling its use in academic disciplines, and examining AI's societal implications.Dan Jurafsky @jurafsky
27K Followers 297 Following Professor of linguistics and professor of computer science at Stanford and author of the James Beard award finalist "The Language of Food"Percy Liang @percyliang
50K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianistrishi @RishiBommasani
4K Followers 2K Following Stanford CS PhD @StanfordCRFM @StanfordNLP @StanfordAILab @StanfordHAI Advisers: @percyliang @jurafsky Previous: @CornellCIS @clairecardie #FoundationModelsMMLU is the standard LM evaluation but model developers (i) use different prompting strategies and (ii) often do not release prompts. 3rd-party researchers often obtain lower scores 🤯 📢 HELM MMLU uses simple, standardized prompts, resulting in fair, reproducible comparisons of…
Pleased to share this paper (my first solo-authored) has been accepted to #ICML2024 :)
The attention mechanism of Transformers resembles a modern iteration of associative memory models from neuroscience. I show auto- & hetero-associative mixtures can perform a range of tasks + suggest new neuro-inspired Transformer interp approaches. Link: arxiv.org/abs/2404.07123
My typical day as a Member of Technical Staff at OpenAI: [9:00am] Wake up [9:30am] Commute to Mission SF via Waymo. Grab avocado toast from Tartine [9:45 am] Recite OpenAI charter. Pray to optimization Gods. Learn the Bitter Lesson [10:00am] Meetings (Google Meet). Discuss how to…
I'll be in: - Vienna, Austria 🇦🇹 for @iclr_conf 6-11 May - Leipzig, Germany 🇩🇪 to visit @mpiMathSci 13-17 May - Okinawa & Tokyo, Japan 🇯🇵 for my @OISTedu graduation ceremony + to visit @ArayaGlobal 22 May - 4 June Reach out if you'd like to meet up :)
Can't wait for #ICLR2024? Check out the new @ClimateChangeAI blog post - our recap of our #NeurIPS2023 workshop, including summaries of the best papers. Read the full post here 👇climatechange.ai/blog/2024-04-1…
This is the paper I wish I had when I started working on LLMs -- a thorough discussion of the unique opportunities/challenges of interpreting LLMs and using LLMs for interpretation
Microsoft presents Rethinking Interpretability in the Era of Large Language Models paper page: huggingface.co/papers/2402.01… Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural…
Would folks be interested if I started a CHAT-ABOUT-ANYTHING (research, career, interviews) office hours? Drop me a line and we can set up a time 💬 Thanks to @thegautamkamath, @bneyshabur, and @hsnfirooz for the inspiration👇🏼 x.com/bneyshabur/sta… x.com/hsnfirooz/stat…
Wanna chat about... anything? Research, academia, hot chicken sandwiches, or anything else! Join my open office hours tomorrow at 9 AM Eastern. I'll drop the link below around that time (or click through find it in the Google Calendar event description)
The folks at @OpenAI and @ericschmidt were kind enough to give @AdtRaghunathan and me a generous gift to better understand supervision with weak models. We are honored to be awarded, and are looking forward to the exciting work that will come out of this !
NeurIPS should not be doing a high school track. The main effect will be to give the most-privileged yet another tool with which to outcompete less-privileged kids on college admissions. We need more paths for getting into research at *later* stages of life, not earlier ones.
I don't say yes to high school students because I think that is a good way to skew our research community even more towards the most privileged. Exception is if it's deliberately a program at a high school that is emphatically not for students like that
The superalignment fast grants are now decided! We got a *ton* of really strong applications, so unfortunately we had to say no to many we're very excited about. There is still so much good research waiting to be funded. Congrats to all recipients!
Headed to the Netherlands to give a keynote at Utrecht symposium on ML & explainability bringing together ML and PhilSci scholars. Who's around & what's happening in Amsterdam this weekend? ✈️🤖🎷🍾
Have you ever done a dense grid search over neural network hyperparameters? Like a *really dense* grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish colors to hyperparameters for which training diverges.
Happy to share I’ve started a new position as a Postdoc at @Cornell's new SciAI Center. I'll be working towards understanding AI, especially Transformers and Large Language Models like ChatGPT, from a neuroscience perspective. Please reach out if and when you're visiting Ithaca!
Just finished my first term teaching Intro to ML at @WaterlooENG and incredibly honored to receive the Igor Ivkovic Teaching Excellence Award! From the bottom of my heart, big thanks to my students & @UWaterloo for making our classrooms a vibrant hub of scientific curiosity! 🎓✨
Hey! Enjoying INVICTA so far? Let us show you some of the highlights of the Day 5 of this Spring School! On Day 5, powered by @aisym4med and @FhP_AICOS, we learned about learning from synthetic data with Fadi Boutros, on behalf of Naser Damer.
This is us! ☺️
Neues Instrument der @LeibnizWGL fördert 4 institutsübergreifende Vorhaben. Das Ziel: einen starken Beitrag zur Lösung gesellschaftlich drängender Fragestellungen zu leisten. @LeibnizATB ist an zwei der geförderten #LeibnizLabs beteiligt. Wir freuen uns! 📰atb-potsdam.de/de/aktuelles-u…
Hey! Are you ready for INVICTA? We are waiting for you! See you in Porto Innovation Hub! invicta.inesctec.pt @INESCTEC #invictaschool #springschool #meaningfulpatterns #visualintelligence #computervision #machinelearning #AI
Join us in beautiful Malta this summer ☀️ We are organizing a special track on global explainability at xAI-2024 and we invite all researchers and practitioners in the field of #ExplainableAI to submit their works! xaiworldconference.com/2024/call-for-…
Impressive 👀
Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵 dpmd.ai/3TiYV7d
Great work from @soniajoseph_! Frontier models are multimodal, and it's increasingly clear that mechanistic interpretability can't only study language models. Good tooling is unglamorous to work on, but essential for good research. I'm excited to see what work Prisma enables!
I'm excited to release Prisma, a mechanistic interpretability library for multimodal models like CLIP and ViTs. Incubated at @tyrell_turing's lab & in collab with @NeelNanda5. Recent mech interp work has focused on language, but many techniques transfer. Behold, the dogit lens: