Siyuan Guo @syguoML
PhD Student in ML with @Cambridge_Uni @MPI_IS. Working on Causal Exchangeability and AI4Science. 🇨🇳 siyuanguo.com Joined May 2021-
Tweets84
-
Followers507
-
Following164
-
Likes141
Build what you need and use what you build. This is a core philosophy of my research. It shifts the focus away from publishing “papers” to what really matters — impact. This thread unpacks why I think this is a successful approach to science. 1/10 Or see: perceiving-systems.blog/en/post/build-…
The Cambridge Ellis Unit Summer School on Probabilistic Machine Learning is from 15-19 July 2024 at the Cambridge Department of Computer Science and Technology. Application deadline: 8 May 2024 Admission notification by: 22 May 2024 More information: ellis.eng.cam.ac.uk/summer-school/
Led by @yaxi_hu, in collaboration with @bschoelkopf, we quantify the privacy degradation due to non-private preprocessing. Main takeaway is that it can be controlled even when preprocessing introduces correlation between ALL points in dataset. Paper: arxiv.org/abs/2403.13041
Led by @yaxi_hu, in collaboration with @bschoelkopf, we quantify the privacy degradation due to non-private preprocessing. Main takeaway is that it can be controlled even when preprocessing introduces correlation between ALL points in dataset. Paper: arxiv.org/abs/2403.13041
I will soon be hiring another PhD student to work with me at @DIKU_Institut @MLSectionUCPH in topics related to 1⃣ Trustworthy ML (Differential privacy, Robustness) and 2⃣ Leveraging unlabelled data in ML Reach out to me via DM/email if you are interested and spread the word!
Excited about this new preprint with Daniil and @kristo arxiv.org/abs/2402.16778 We show a Ω(log T) lower bound for Differentially Private Online learning, even for finite Littlestone classes. This shows a separation between DP and non-DP online learning in mistake bound model.
Thank you @AleksanderMolak for the nice intro! Indeed, we view data heterogeneity, especially the regime of exchangeable but not i.i.d. data, as an opportunity for causality. Our work shows exchangeable data has extra conditional independence structures that i.i.d. data lacks -…
Thank you @AleksanderMolak for the nice intro! Indeed, we view data heterogeneity, especially the regime of exchangeable but not i.i.d. data, as an opportunity for causality. Our work shows exchangeable data has extra conditional independence structures that i.i.d. data lacks -…
I went on a tour giving talks on AI to high-schoolers in Transylvania. In the school I was going to visit on Wednesday, Tamási Áron School, a roof collapsed today, killing a teenager, leaving another in coma please donate to their families and peers here gofund.me/0711ded7
Very exciting to see Goutham Rajendran, @rpatrik96, Pradeep Ravi Kumar, @wielandbr connecting causal de Finetti to dynamical systems. We believe humans discover causal relationships through exploration in time, and we need to understand how.
Very exciting to see Goutham Rajendran, @rpatrik96, Pradeep Ravi Kumar, @wielandbr connecting causal de Finetti to dynamical systems. We believe humans discover causal relationships through exploration in time, and we need to understand how.
If you’re at @NeurIPSConf today, come check out our work (oral 2C Causality, 3:55-4:10pm) led by Junhyung Park. Jun is now on a job market (junhyung-park.github.io).
If you’re at @NeurIPSConf today, come check out our work (oral 2C Causality, 3:55-4:10pm) led by Junhyung Park. Jun is now on a job market (junhyung-park.github.io).
Day 1 @ NeurIPS 2023: @lindensli's talk is fantastic, do check out the slides once available! It explains with such clarity the tools used daily for LLM inference speed-up and its underlying principles, e.g., tensor parallelism, vllm. Highlights are: 1. LLM inference on GPU…
Day 1 @ NeurIPS 2023: @lindensli's talk is fantastic, do check out the slides once available! It explains with such clarity the tools used daily for LLM inference speed-up and its underlying principles, e.g., tensor parallelism, vllm. Highlights are: 1. LLM inference on GPU…
I will be at NeurIPS 2023 from Dec 10 to Dec 17! DM if you want to chat about causal abstraction, AI safety and alignment, reward hacking! #NeurIPS2023 #aisafety #causalai
Patrik Reizinger @rpatrik96
950 Followers 150 Following 🇭🇺 🇪🇺 PhD student in ML @uni_tue, IMPRS-IS @MPI_IS, @ELLISforEurope. Causal representation learning, identifiability. https://t.co/TPP2SvzXATKrikamol@CISPA @krikamol
2K Followers 1K Following Chief Scientist/Faculty at Rational Intelligence (RI) Lab @CISPA; Chief Research Officer (CRO) @ https://t.co/DSonRM9oDA; Previously @MPI_IS, @MahidolU, @uclcs, @GatsbyUCL.Dan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)Zhijing Jin @ZhijingJin
3K Followers 1K Following Final-year PhD @MPI_IS & @ETH_en w/ @bschoelkopf. Research on (1) @CausalNLP and (2) NLP4SocialGood @NLP4SG. Mentor and mentee @ACLMentorship.Julius von Kügelgen @JKugelgen
2K Followers 323 Following Postdoc with Jonas Peters at ETH. Interested in causal inference and machine learning. PhD from @MPI_IS and @CambridgeMLG. Banner credit: @xkcd.Cristian Bodnar @crisbodnar
5K Followers 2K Following Senior Researcher @MSFTResearch | Simulations, Geometric Deep Learning, AI4ScienceNaomi 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.Vincent Stimper @VStimper
751 Followers 372 Following PhD student in Machine Learning at @Cambridge_Uni and @MPI_IS | Incoming Research Scientist @IsomorphicLabs. Former research intern at @Microsoft and @Amazon.Tycho van der Ouderaa @tychovdo
1K Followers 2K Following Postgraduate researcher (PhD) at Imperial College London and visiting researcher at the University of Oxford. Working on probabilistic machine learning.Limor Gultchin @gultchin
658 Followers 910 Following VP of AI/ML @ Berkshire Partners. CompSci PhD from University of Oxford/Turing Institue. Internships at DeepMind, Google.Siu Lun Chau @Chau9991
337 Followers 479 Following Postdoctoral Researcher at the Rational Intelligence Lab @CISPA; Previously at @oxcsml, @AmazonUK, @MPI_IS.D @dylan_works_
190 Followers 785 FollowingKlaus-Rudolf Kladny @KladnyKlaus
31 Followers 101 Following PhD student @ Max Planck Institute for Intelligent Systems. Ex ETH Zürich. Interested in causality & deep learning.Yichao Liang @yichao_liang
175 Followers 1K Following Student of AI @CambridgeMLG, @Oxford_VGG & @MITCoCoSci. Polymath-aspiring.Eva Louise Marie Gabr.. @e681554349
9 Followers 3K FollowingInwoo Hwang @InwooRyanHwang
117 Followers 490 Following PhD student @ Seoul National University, w/@sanghack. Interested in the intersection of causality and machine learning. Currently looking for internship in 2024Emmanuel Esposito @emmanuelespo
72 Followers 243 Following PhD student in Computer Science at University of Milan @LaStatale & IITGiorgia Ramponi @gio_ramponi
1K Followers 169 Following Assistant professor at @UZH_en - prev. @ETH_AI_Center - @Google 🌼 Working on RL, multi-agent, imitation learning, and other sequential decision-making stuffClaire Vernade @vernadec
4K Followers 942 Following I tweet on Machine Learning, mostly Bandits, RL and Learning Theory. Group Leader in Tübingen @ml4science. ex-Deepmind. Activist in tech.Botos Csabi @csaba_botos
180 Followers 238 Following PhD candidate in Torr Vision Group, University of Oxford https://t.co/WzU6h3qhagChaoren Shen @seaborg2012
28 Followers 212 Following ECNUer_Shanghai, DFT, organometallic, Wikipedia Editor, Rail BuffThelma @larsonthelma16
143 Followers 3K FollowingAshish Yashwanth @ashishkangen
5 Followers 123 FollowingMehrnaz Bahrami @MehrB_11
20 Followers 435 FollowingRachel Velez @RachelVele63257
163 Followers 3K Followingandy bartlett @getoffmyline
133 Followers 686 Following what is the question. fapp is not the answer. community lawyer in the bay areaSalman Khan @salmanukkhan
8 Followers 549 FollowingNan @barnesnan56
133 Followers 3K FollowingJundeWu @JundeMorsenWu
204 Followers 940 Following Creating AI to make human work less & live longer. Phd @UniofOxford. Prev. Tech Leader @Baidu_Inc. Funder of Panoptes (acq. by @SenseTime_AI).Nicoleta Spînu @nicospinu
485 Followers 523 Following Modelling, simulation & education @esqLAB. Opinions are my own.Laura Iacovissi @liacov95
17 Followers 75 Following PhD student at https://t.co/X40YoXGHZ5, University of TübingenMark Goldstein @marikgoldstein
952 Followers 1K Following machine learning phd at NYU, previously new england conservatory of music, harvard cs, riken tokyo. absolutely discontinuous with respect to Lebesgue measure.Alexander Strudwick Y.. @AlexTISYoung
4K Followers 2K Following Statistical geneticist @ UCLA & part of the SSGAC. Oxford PhD. Research how we can use family data to disentangle nature and nurture. Methods developer.Iñigo Bermejo @inigobermejo
43 Followers 218 Following Assistant Professor at Hasselt University, interested in machine learning, artificial intelligence, prediction modelling and causal inference.Ayush Sawarni @ayushsawarni
71 Followers 476 FollowingAleksander Molak (at .. @AleksanderMolak
2K Followers 1K Following Causality for Machine Learners: https://t.co/n5xASwzYSu Podcast: https://t.co/4FWOtSWRDj Best-Selling Author || Advisor Teaching Causality @ Oxford TLV/WAWDr. Jakob Zscheischle.. @ZscheischlerJak
2K Followers 2K Following Climate scientist @ufz_de & Prof @tudresden_de, interested in #extremes, #carboncycle #ML @compound_EventChristine Herlihy @crherlihy
692 Followers 5K Following PhD candidate @umdcs 👩🏻💻 | on the job market 🌿 ML/AI, RL | sequential decision-making | algorithmic fairness | knowledge representation & reasoning✨she/herFabio Motoki @fmotoki
72 Followers 878 Following Using analytics and delivering projects to improve businesses.Rohan Jain @JainRohan16
106 Followers 416 Following • MSc Student in ML Theory @UCalgary 🇨🇦 | ML Researcher @ml_collective 🌎 • Prev: Math + CS @UofTTr(𝐀) @leakedweights
51 Followers 486 Following I put the intractable into the normalization constantThuto @Thuto227728
145 Followers 1K FollowingAgam Goyal @ag_endure
22 Followers 274 Following Incoming CS PhD @IllinoisCS | BS Computer Science, Mathematics, and Data Science @UWMadison '24DaoMinhKhanh @Khanhdaominh1
13 Followers 220 FollowingYuntian Deng @yuntiandeng
3K Followers 3K Following #NLProc Postdoc @ai2_mosaic | Assistant Professor @UWaterloo '24 | Faculty Affiliate @VectorInst '24 | PhD @Harvardpkms🍕 @PrakamyaMishra
701 Followers 1K Following Applied Research Engineer @AMD | Researcher @ BioNLP Lab @manningcics | Ex-Applied Scientist Intern @AmazonScience | MS CS @manningcicsYorgos Felekis @yfelekis
322 Followers 757 Following PhD student in Machine Learning and Causality @uniofwarwick | Member of Warwick Machine Learning Group https://t.co/mhpFczYtQa | 🧪🖥️jooeyzz @jooeyzz
124 Followers 3K Followingdan @samhsinv
20 Followers 556 FollowingAaditya Ura ( looking.. @aadityaura
715 Followers 884 Following ML Researcher | Focus on Representation Learning on Graphs and Manifolds | NLP | Generative Modeling | Healthcare - Looking for a funded PhDPablo Rodríguez Mier @PabloRMier
994 Followers 1K Following Scientist at @saezlab, @uniklinik_hd, Heidelberg University. Mathematical modeling / ML & AI for biological systems. @[email protected]Apostolos Lymperis @ApostolosLymp
137 Followers 177 Following Commercialising Causal AI at @causaLensSahil Jain @SahilJain314
31 Followers 118 Following professional tensorboarder. Deep Learning Algos @NVIDIAFerenc Huszár @fhuszar
40K Followers 1K Following Secular Bayesian. Associate Professor in Machine Learning @Cambridge_CL. Talent aficionado at https://t.co/RbJkoLguey Alum of @Twitter, Magic Pony and @BaldertonPatrik Reizinger @rpatrik96
950 Followers 150 Following 🇭🇺 🇪🇺 PhD student in ML @uni_tue, IMPRS-IS @MPI_IS, @ELLISforEurope. Causal representation learning, identifiability. https://t.co/TPP2SvzXATAndrej Karpathy @karpathy
978K Followers 904 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Krikamol@CISPA @krikamol
2K Followers 1K Following Chief Scientist/Faculty at Rational Intelligence (RI) Lab @CISPA; Chief Research Officer (CRO) @ https://t.co/DSonRM9oDA; Previously @MPI_IS, @MahidolU, @uclcs, @GatsbyUCL.Zoubin Ghahramani @ZoubinGhahrama1
24K Followers 615 Following VP Research, Google DeepMind, ex-head of Google Brain. Professor at University of Cambridge. Machine Learning Researcher. ex-Chief Scientist & VP of AI, Uber.Zhijing Jin @ZhijingJin
3K Followers 1K Following Final-year PhD @MPI_IS & @ETH_en w/ @bschoelkopf. Research on (1) @CausalNLP and (2) NLP4SocialGood @NLP4SG. Mentor and mentee @ACLMentorship.Julius von Kügelgen @JKugelgen
2K Followers 323 Following Postdoc with Jonas Peters at ETH. Interested in causal inference and machine learning. PhD from @MPI_IS and @CambridgeMLG. Banner credit: @xkcd.Sergey Levine @svlevine
79K Followers 122 Following Associate Professor at UC Berkeley Co-founder, Physical IntelligenceShane Gu @shaneguML
28K Followers 1K Following Research Scientist & Manager @GoogleDeepMind Tokyo/MTV. ex: @GoogleAI Brain, @OpenAI. (JP: @shanegJP)Arthur Gretton @ArthurGretton
9K Followers 730 Following Professor in Machine Learning, Gatsby Computational Neuroscience Unit Research Scientist, Google DeepMind @[email protected]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.David Krueger @DavidSKrueger
13K Followers 4K Following Cambridge faculty - AI alignment, deep learning, and existential safety. Formerly Mila, FHI, DeepMind, ElementAI, AISI.Vincent Stimper @VStimper
751 Followers 372 Following PhD student in Machine Learning at @Cambridge_Uni and @MPI_IS | Incoming Research Scientist @IsomorphicLabs. Former research intern at @Microsoft and @Amazon.Limor Gultchin @gultchin
658 Followers 910 Following VP of AI/ML @ Berkshire Partners. CompSci PhD from University of Oxford/Turing Institue. Internships at DeepMind, Google.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Uri Shalit @ShalitUri
6K Followers 1K Following Machine learning researcher, working on causal inference and healthcare applications. Associate prof @TechnionLive @[email protected] @urish.bsky.socialSiu Lun Chau @Chau9991
337 Followers 479 Following Postdoctoral Researcher at the Rational Intelligence Lab @CISPA; Previously at @oxcsml, @AmazonUK, @MPI_IS.Klaus-Rudolf Kladny @KladnyKlaus
31 Followers 101 Following PhD student @ Max Planck Institute for Intelligent Systems. Ex ETH Zürich. Interested in causality & deep learning.Bálint Mucsányi @BalintMucsanyi
144 Followers 97 Following MSc Machine Learning @ University of TübingenEmmanuel Esposito @emmanuelespo
72 Followers 243 Following PhD student in Computer Science at University of Milan @LaStatale & IITGiorgia Ramponi @gio_ramponi
1K Followers 169 Following Assistant professor at @UZH_en - prev. @ETH_AI_Center - @Google 🌼 Working on RL, multi-agent, imitation learning, and other sequential decision-making stuffMassimiliano Pontil @MPontil
213 Followers 78 Following Researcher @IITalk, Prof @UCL, co-director @EllisGenoa Machine Learning and StatisticsClaire Vernade @vernadec
4K Followers 942 Following I tweet on Machine Learning, mostly Bandits, RL and Learning Theory. Group Leader in Tübingen @ml4science. ex-Deepmind. Activist in tech.Botos Csabi @csaba_botos
180 Followers 238 Following PhD candidate in Torr Vision Group, University of Oxford https://t.co/WzU6h3qhagTu Vu @tuvllms
3K Followers 894 Following Research Scientist @GoogleDeepMind & Assistant Professor @VT_CS. PhD from @UMass_NLP. #NLProcAleksander Molak (at .. @AleksanderMolak
2K Followers 1K Following Causality for Machine Learners: https://t.co/n5xASwzYSu Podcast: https://t.co/4FWOtSWRDj Best-Selling Author || Advisor Teaching Causality @ Oxford TLV/WAWMehran Kazemi @kazemi_sm
1K Followers 497 Following Senior Research Scientist @GoogleAI. Research areas: machine/deep learning, large language models, artificial general intelligence. Views my own.Yuntian Deng @yuntiandeng
3K Followers 3K Following #NLProc Postdoc @ai2_mosaic | Assistant Professor @UWaterloo '24 | Faculty Affiliate @VectorInst '24 | PhD @HarvardMichael C. Mozer @mc_mozer
634 Followers 56 Following Research Scientist, Google Brain where cognitive science and machine learning meetSahil Jain @SahilJain314
31 Followers 118 Following professional tensorboarder. Deep Learning Algos @NVIDIALisa Alazraki @LisaAlazraki
652 Followers 791 Following #ML & #NLProc PhD student @ImperialCollege. Prev. research intern @GoogleAI. Reasoning, planning & LLMs as agents. Reposted papers are my reading list 📚Victoria X Lin @VictoriaLinML
3K Followers 761 Following Research Scientist @AIatMeta Foundational AI Research • ex-@SFResearch • PhD @uwcse 📜 https://t.co/j6QTac5q0rMiles Cranmer @MilesCranmer
12K Followers 903 Following Assistant Prof @Cambridge_Uni, works on AI for the physical sciences. Previously: Flatiron, DeepMind, Princeton, McGill.Yao Fu @Francis_YAO_
13K Followers 2K Following PhD @EdinburghNLP on LLMs and Machine Reasoning. Ex. @Columbia @PKU1898 @MITIBMLab @allen_ai AGI has yet to come, so keep runningSang Michael Xie @sangmichaelxie
3K Followers 709 Following PhD student @StanfordAILab @StanfordNLP @Stanford advised by Percy Liang and Tengyu Ma. Prev: visiting @GoogleAI Brain, BS, MS Stanford ‘17Gowthami Somepalli @gowthami_s
6K Followers 979 Following Grad student @UMDCS. Past: @AIatMeta, @AmazonScience, @IITMadras. Currently working on #Diffusion and #Multimodal understanding. GPU poor. She/her.Martin Gubri @framart1
324 Followers 796 Following Research Lead @parameterlab working on Trustworthy AI | he/him @[email protected]Hongyu Ren @ren_hongyu
3K Followers 595 Following Research Scientist @openai. CS PhD @stanford. Previously @apple, @googleai and @nvidiaai. I train language models.Prof. 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.Roberta Raileanu @robertarail
4K Followers 1K Following Research Scientist @Meta & Honorary Lecturer @UCL. ex @DeepMind | @MSFTResearch | @NYU | @Princeton. Llama-3, Toolformer, Rainbow Teaming.NewInML @ NeurIPS 202.. @NewInML
957 Followers 46 Following NewInML @ NeurIPS 2023 Check our website!Xinyun Chen @xinyun_chen_
4K Followers 840 Following Research Scientist at @GoogleDeepMind. PhD from @Berkeley_EECS.SIAM Activity Group o.. @DynamicsSIAM
10K Followers 2K Following The X account of Society for Industrial and Applied Mathematics activity group on Dynamical Systems. Managed by activity-group officers. https://t.co/StVrDaPXwbTogether AI @togethercompute
27K Followers 303 Following The future of AI is open-source. Let's build together.Shunyu Yao @ShunyuYao12
7K Followers 856 Following Language agents (ReAct, Reflexion, Tree of Thoughts) for digital automation (WebShop, SWE-bench, SWE-agent)Jessica Schrouff @JessicaSchrouff
2K Followers 492 Following Senior Research Scientist @DeepMind. Interested in machine learning, trustworthy ML, causality, health, diversity, inclusion and equity. She/her.Rickard Karlsson @RdKarlsson
295 Followers 228 Following PhD student working on causal inference & ML @tudelftJiashuo Liu @liujiashuo77
297 Followers 324 Following Visiting Student Researcher @StanfordEng (MS&E) | CS PhD @Tsinghua_Uni | remote @Columbia DRO | OOD Generalization, Robust Optimization, Data-Centric AINouha Dziri @nouhadziri
3K Followers 671 Following Research Scientist @allen_ai / @ai2_mosaic, PhD in NLP/Dialogue 🤖 UofA. Ex Visiting researcher @Mila_Quebec Ex Research intern at @GoogleDeepMind @MSFTResearchFAR AI @farairesearch
1K Followers 19 Following Ensuring AI systems are trustworthy and beneficial to society by incubating new AI safety research agendas.Anirudh Goyal @anirudhg9119
5K Followers 486 Following Gemini ♊ Spent time at @Berkeley_EECS, @MPI_IS, @DeepMind.Ching-An Cheng @chinganc_rl
2K Followers 84 Following Senior Researcher at @MSFTResearch, working on usable theory and algorithms for Reinforcement Learning and Robotics.PolymathicAI @PolymathicAI
2K Followers 77 Following The Polymathic AI Collaboration. Shared account.Dan Hendrycks @DanHendrycks
17K Followers 81 Following • Director of the Center for AI Safety (https://t.co/ahs3LYCpqv) • GELU/ImageNet-C/MMLU/safety groundwork • PhD in AI from UC Berkeley https://t.co/rgXHAnYAsQ https://t.co/YtGtDh1aAVlmsys.org @lmsysorg
37K Followers 171 Following Large Model Systems Organization. We created Vicuna and Chatbot Arena! Compare 30+ LLMs (GPT-4/Claude/Llamas) side-by-side at https://t.co/IDFeIDIOtmDavid Dohan @dmdohan
8K Followers 1K Following reducing perplexity @openai | past: probabilistic programs, proteins, science & reasoning @ google brain 🧠Karthika Mohan @Carthica
1K Followers 541 Following Asst. Professor (Computer Science), Oregon State University Postdoc UC Berkeley, PhD UCLA (J Pearl) Artificial Intelligence, Causal Inference, Graphical ModelsLed by @yaxi_hu, in collaboration with @bschoelkopf, we quantify the privacy degradation due to non-private preprocessing. Main takeaway is that it can be controlled even when preprocessing introduces correlation between ALL points in dataset. Paper: arxiv.org/abs/2403.13041
Our work with @AmartyaSanyal and @bschoelkopf on privacy of pre-processing is online. Exciting conclusion: Non-private data-dependent pre-processing can be integrated into a DP ML pipeline with minimal degradation of privacy. Paper: arxiv.org/abs/2403.13041 Visualisation 👇
Happy to share what I have been working on for awhile: Generalist agent that can follow natural language insurrections in a board range of games!
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
My PhD is coming to an end, and I'm excited to join @IsomorphicLabs as a Machine Learning Research Scientist soon. I'll be working in the Lausanne office starting in June. Very much looking forward to working on advancing drug discovery with AI!
I will soon be hiring another PhD student to work with me at @DIKU_Institut @MLSectionUCPH in topics related to 1⃣ Trustworthy ML (Differential privacy, Robustness) and 2⃣ Leveraging unlabelled data in ML Reach out to me via DM/email if you are interested and spread the word!
I’m grateful to the team of incredible women behind the organisation of this special workshop for IWD. Looking forward to it!
We are thrilled to announce our lineup of speakers from @uni_tue, @MPI_IS, @ml4science!💫 Caterina De Bacco @AlbaneRuaud @UlrikeLuxburg Ana Andreea Stoica The talks will be followed by an amazing panel: "Ask me anything!", moderated by @vernadec Join us!
The room was almost completely full until the last minute. Our participants shared their thoughts and insights, sparking more engaging discussions. A summary tomorrow. At our Causal Parrots Workshop @RealAAAI #aaai2024 @devendratweetin @matej_zecevic
Excited about this new preprint with Daniil and @kristo arxiv.org/abs/2402.16778 We show a Ω(log T) lower bound for Differentially Private Online learning, even for finite Littlestone classes. This shows a separation between DP and non-DP online learning in mistake bound model.
[somehow the rest of this thread did not go through: ] A huge thanks to my two amazing supervisors @bschoelkopf at @MPI_IS and @adrian_weller at @CambridgeMLG for believing in me, giving me the freedom to explore, and for all their insights, support, and advice over the years!
On Friday, I successfully defended my PhD thesis "Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment" in Cambridge, examined by Profs @jmhernandez233 and @RavikumarPrad. I'm particularly delighted to have passed with no corrections 🎉
On Friday, I successfully defended my PhD thesis "Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment" in Cambridge, examined by Profs @jmhernandez233 and @RavikumarPrad. I'm particularly delighted to have passed with no corrections 🎉
When I’m writing my paper, I exist in only 2 states. 1) Mm, this came out nicely, 2) It’s the worst among all the projects I’ve done and I should be banished from ML. #phdlife #imontwittersomuchtodaycuzimwriting
Yisss 😎 Gave a talk about our latest paper, Label Delay in Continual Learning at @GoogleDeepMind, thanks to the kind invitation of Razvan Pascanu. You can find the project page here: botcs.github.io/label-delay/
ooh, fun game. my most-cited, never-accepted, arXiv-only paper [722 citations]: "Bayesian active learning for classification and preference learning" N Houlsby, F Huszár, Z Ghahramani, M Lengyel
My most-cited, never-accepted, ArXiv-only paper has over 1880 citations. "Deep Convolutional Networks on Graph-Structured Data" Mikael Henaff, Joan Bruna, Yann LeCun arxiv.org/abs/1506.05163
🥳Very happy that all our three submissions are accepted to ICLR 2024! G-Shell is accepted as Oral and MetaMath as Spotlight! This year's ICLR batch well represents my current research focus. 1/6
Is causality necessary for trustworthy and explainable systems? From fair bandits to counterfactual explanations and back. 1/n #causality #causalinference #fairness #machinelearning #explainability #trustworthyAI #causaltwitter
What if we could discover the true causal structure from observational data? Too good to be true? 1/n #causaltwitter #causality #machinelearning #causaldiscovery
If you’re still at #NeurIPS2023 and curious about #causal #explainable #AI, drop by our poster at the XAI in Action Workshop at 4:30pm 📊 xai-in-action.github.io/#schedule Also generally happy to chat about #algorithmicRecourse, #conceptLearning, and/or #humanAI #collaboration 🤖💪🏼🦾🧠
1/7 🚨Excited to share our #ICML2023 paper w/ @krikamol, @skornblith, @bschoelkopf, @_beenkim. We explore the link between model predictions (Y) & their explanations (E) using the Potential Outcomes framework. arxiv.org/abs/2212.06925 🧵👇🏼
Super interesting panel at the Generative AI for Biology workshop right now at #NeurIPS2023. One point I loved by @kchonyc is that the ultimate vision of foundation models here must be to link patient outcomes all the way down to the atom level.
If you’re at @NeurIPSConf today, come check out our work (oral 2C Causality, 3:55-4:10pm) led by Junhyung Park. Jun is now on a job market (junhyung-park.github.io).
(2/2) How can we axiomatize causality? In our NeurIPS oral, “A Measure-Theoretic Axiomatisation of Causality", we introduce causal spaces as an extension of probability theory, addressing issues like cycles, latent variables, and stochastic processes. #NeurIPS2023 #Causality
Mixtral 8x7B is here, 11 weeks only after Mistral 7B. Outperforms Llama 2 70B and GPT 3.5 on most benchmarks, at the inference cost of a 12B dense model, with 32k tokens context size.