Sam Buchanan @_sdbuchanan
Research Assistant Professor @TTIC_Connect, PhD @EE_ColumbiaSEAS. Working on mathematical foundations of modern data-driven signal processing (deep learning!) sdbuchanan.com Chicago, IL Joined March 2015-
Tweets252
-
Followers641
-
Following905
-
Likes2K
One more post from Seoul -- rented a bike and rode most of the Han River Trail today. Absolutely incredible public resource -- has to be better than any such thing we have in the US (?), and can likely go pound-for-pound with urban trails around Europe too (??)
Very much enjoyed a visit and talk at Prof. Jong Chul Ye's group at KAIST today! Beautiful campus and very interesting research.
Traveling to Seoul tomorrow for our tutorial about white-box deep networks on Sunday. Hope to see you there! cmsworkshops.com/ICASSP2024/tut…
My group at Berkeley Stats and EECS has a postdoc opening in the theoretical (e.g., scaling laws, watermark) and empirical aspects (e.g., efficiency, safety, alignment) of LLMs or diffusion models. Send me an email with your CV if interested!
Passing along in case you (also) hadn't seen it, or not for a while at least -- there are beautiful words about the spirit of analysis in here: "fine cuisine", about "...strength and sharpness of attack with simple, powerful tools" :-)
Passing along in case you (also) hadn't seen it, or not for a while at least -- there are beautiful words about the spirit of analysis in here: "fine cuisine", about "...strength and sharpness of attack with simple, powerful tools" :-)
Thanks for organizing such a wonderful conference and for the invitation. Really glad that the founding organizers have a vision for including neuroscience as one of @CPALconf's focus areas, which includes theory, parsimony, representations, natural and artificial intelligence,…
Thanks for organizing such a wonderful conference and for the invitation. Really glad that the founding organizers have a vision for including neuroscience as one of @CPALconf's focus areas, which includes theory, parsimony, representations, natural and artificial intelligence,…
This afternoon CPAL has two tutorials on the theory and algorithms on deep learning and inverse problems, respectively: cpal.cc/tutorials/ They are open to all students.
Yi Ma @YiMaTweets kicking off the inaugural CPAL 2024 @CPALconf ! Looking forward to a great week of talks
All programs and preparations are final for the new CPAL conference: cpal.cc is final. Nearly 200 people registered for this new conference, with many new features. Look forward to seeing many friends. What a way to celebrate the new year 2024 in Hong Kong!
Yi Ma @YiMaTweets
71K Followers 123 Following Chair Professor in AI, Director of IDS, Head of CS, HKU; Professor of EECS, Berkeley; Author of Book: High-Dim Data Analysis, https://t.co/gwaqMJp8av.Maxim Raginsky @mraginsky
8K Followers 2K Following father, academic, raconteur, aging wannabe hipster blog: https://t.co/akk6LCvKw6Dan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)Amin Karbasi @aminkarbasi
8K Followers 2K Following Associate Professor at Yale University, staff research scientist at Google.Dimitris Papailiopoul.. @DimitrisPapail
11K Followers 975 Following prof @ wisconsin; thinking about transformers; learning in context; babas of Inez LilyJason Lee @jasondeanlee
10K Followers 3K Following Associate Professor at Princeton and Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learningAryeh Kontorovich @aryehazan
4K Followers 470 Following probability, statistics, metric spaces, Markov chains, freedom (social & academic), Israel, Jew stuff. opinions represent my employer & all other groups I'm inSoledad Villar @SoledadVillar5
3K Followers 2K Following Applied math/data science/ML Assistant Professor at Johns Hopkins. She/ella. Uruguaya 🇺🇾Tom Goldstein @tomgoldsteincs
23K Followers 2K Following Professor at UMD. AI security & privacy, algorithmic bias, foundations of ML. Follow me for commentary on state-of-the-art AI.Shubhendu Trivedi @_onionesque
7K Followers 851 Following Cultivated Abandon. Twitter interests: Machine learning research, applied mathematics, mathematical miscellany, ML for Physics/Chemistry, books.Alex Dimakis @AlexGDimakis
13K Followers 2K Following UT Austin Professor. Researcher in Machine Learning and Information Theory. National AI Institute on the Foundations of Machine Learning (IFML) Co-director.Preetum Nakkiran @PreetumNakkiran
10K Followers 2K Following ML research @Apple. @sh_reya’s fiancé | PhD @Harvard, postdoc @UCSanDiego, EECS @Berkeley_EECS, "AI" @OpenAI, @GoogleAIUlugbek S. Kamilov @ukmlv
4K Followers 2K Following Visiting Prof at ENS Paris. Associate Prof of EE/CS at WashU. Ex Google, MERL, Stanford, MIT, CMU, EPFL. Tennis player. I don’t eat animals. Ўзбекча гапираман.Anastasios Nikolas An.. @ml_angelopoulos
3K Followers 785 Following @Berkeley_EECS Ph.D. with Mike Jordan/Jitendra Malik. Conformal prediction, distribution-free uncertainty quantification, vision/imaging. Former @stanford_ee.Jeremy Cohen @deepcohen
4K Followers 870 Following PhD student in machine learning at Carnegie Mellon. The goal of my research is to turn deep learning into a real engineering discipline.Sam Power @sp_monte_carlo
17K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. (he / him)Damek Davis @damekdavis
3K Followers 631 Following Optimization/ML Learning a little about lean https://t.co/cQ1yukSnEQGautam Goel @gautamcgoel
4K Followers 415 Following Postdoc studying ML at the Simons Institute at UC Berkeley.Cengiz Pehlevan @CPehlevan
2K Followers 1K Following Theoretical neuroscience, theory of neural computation. Assistant Professor of Applied Mathematics @Harvard SEASKangwook Lee @Kangwook_Lee
2K Followers 675 Following Assistant Professor, ECE, UW-Madison / Leading deep learning research @ KRAFTONLetitiaByron @Od9hvp77QTu70i
0 Followers 104 FollowingRuilong Li @ruilong_li
665 Followers 216 Following PhD student at @berkeley_ai | Alumni of @GoogleAI, @RealityLabs, @USC_ICT, @Tsinghua_UniWilliam de Vazelhes @WilldVaz
467 Followers 4K Following PhD candidate at @MBZUAI optim. & ML (esp. iterative hard-thresholding & zeroth-order). Ex @Huawei, Ex @Inria, MSc. @Supelec '16.Elisabetta Cornacchia @Elisabetta68885
63 Followers 91 Following Postdoc at MIT in theoretical machine learningSiddhant Gautam @sidgautam1995
13 Followers 113 Following Ph.D. student @michiganstateu | Prev. @Dolby @iitmadras | MRI Sampling/Reconstruction, X-ray CT Reconstruction, Inverse ProblemsGeonyeong Park @geonyeong_park
42 Followers 52 Following PhD student @KAIST, BISPL lab & BML lab | Diffusion models, Trustworthy and robust AI, Adaptationleonayoon @leonayoon
58 Followers 2K FollowingHyungjin Chung @hyungjin_chung
624 Followers 405 Following Ph.D. student @ KAIST | Writer @AlphaSignalAI | Prev- @GoogleAI @ LANL | Diffusion models for inverse problems, AI4ScienceXuheng Li @xuhengli_
311 Followers 807 Following CS PhD student @UCLA, supervised by @QuanquanGu | RL, deep learning theory, diffusion model | Previously BSc @PKU1898 | StargazerJuan Hmmm @JuanAH03488233
80 Followers 3K FollowingCharlie London @CharlieLondon02
28 Followers 194 Following DPhil student in machine learning theory at Oxford. Supervised by Prof. Varun Kanade.りんちゃん | Rin.. @rinchan_okudera
223 Followers 730 Following 名古屋大学 高田・松原研究室M2 | 組込み研究・勉強中| モノづくりが好き! | 豊橋出身Kento Kawai @kawaisan2000
205 Followers 329 Following Computer Vision / IIM:@Ukita_Lab /MACC:@Matuo_LabChihiro Nakatani @china64681791
118 Followers 132 Following Ph.D. student at Ukita lab (TTI-J). Machine learning and computer vision for human activity analysis (e.g., sport analysis).TTI Ukita Lab. 【豊.. @Ukita_Lab
89 Followers 83 Following 浮田宗伯教授が主宰する豊田工業大学 知能情報メディア研究室です。コンピュータビジョン・画像認識などのマルチメディア計測・認識,および,大規模データの機械学習による計測・認識の高精度化に関する基礎・応用技術を研究しています。Maya Abby🌟✨🩵 @KristinMaya12
323 Followers 776 Following The final happiness of life is the journey towards the final purpose of life. But how many people will be able to travel to the final destination of life?Joe Shenouda @shenouda_joe
113 Followers 152 Following Ph.D. candidate in Electrical and Computer Engineering @ UW-Madison. Interested in machine learning, signal processing and deep learning.Takahiro Maeda @meaten121
72 Followers 170 Following Doctoral student at @Ukita_Lab of Toyota Technological Institute Japan. Certified Care Worker (介護福祉士) Computer Vision/Robotics Profile: https://t.co/JlZKwkVohiJess Sorrell @JessSorrell
206 Followers 404 Following CS postdoc at Penn. Interested in theory of ML and responsible computing. All cat pictures are my own and do not represent the cats of my employer.Rabia Tugce Yazicigil @RabiaYazicigil
63 Followers 161 Following Assistant Professor of ECE at Boston UniversityLisa @BimuclubM
99 Followers 132 Followinglaura @laura012747755
421 Followers 5K FollowingLeon-Leng @LeonLeng5
182 Followers 989 Following PhD student in UW @UW | Alumni @UCBerkeley @cuhksz | Service @CBER_ForumX YZ @SimonSaysMimimi
1 Followers 129 FollowingWuyang Chen @WuyangC
406 Followers 892 Following Ph.D. ECE@UT Austin @utexasece | Postdoc @UCBerkeley | Incoming Asst. Prof. @SFU | Closing the gap b/w DL theory & applications + AI4ScienceJustKeepingUp @justkeepingupml
0 Followers 105 FollowingMcNeetee @MNeetee53515
27 Followers 2K FollowingHamed Hassani @HamedSHassani
2K Followers 669 Following Associate Professor, University of Pennsylvania @PENN, Machine Learning, Information TheoryTobias Uelwer @tuelwer
77 Followers 228 Following Postdoc @TU_Dortmund interested in machine learning and deep learninggalen @galenbrain
79 Followers 367 Following PhD student at UC Berkeley, theoretical neuroscience, vision, ML. The horrors are never-ending yet I remain silly. https://t.co/TdYeYbUChCEhsan Shafiee @Ehsan_Shafiee
255 Followers 531 FollowingGengshan Yang @gengshanY
160 Followers 126 Following Research scientist @RealityLabs. Prev. Ph.D student @CMU_Robotics.Jonathan Wenger @JonathanWenger5
270 Followers 426 Following Postdoc @Columbia. PhD @uni_tue with @PhilippHennig5. I enjoy cycling.INAM KHAN @inamullahnaseeh
186 Followers 4K Following 🚀 BSCS grad 🎓 | Passionate about AI, Machine Learning, and Data Science 💻 | Eagerly seeking internships to dive into the world of cutting-edge tech!Gon Buzaglo @gon_buzaglo
143 Followers 334 Following MSc/BSc student in ECE/(CS+Physics) @TechnionLive. Interested in ML theory, love hiking, diving and jazz musicManoj Acharya @manoja328
579 Followers 5K Following Mostly Interested in safe and aligned (neural inspired) Machine Intelligence ; PhD from Rochester Institute of TechnologyAmrit Singh Bedi @amritsinghbedi3
523 Followers 1K Following CS Faculty at UCF (AlignAI Lab), previous @UMD @ARL @IITK Interested in RL, Nonconvex Optimization, AI text Detection, Federated Learning, RoboticsYann LeCun @ylecun
711K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Yi Ma @YiMaTweets
71K Followers 123 Following Chair Professor in AI, Director of IDS, Head of CS, HKU; Professor of EECS, Berkeley; Author of Book: High-Dim Data Analysis, https://t.co/gwaqMJp8av.Gabriel Peyré @gabrielpeyre
92K Followers 449 Following @CNRS researcher at @ENS_ULM. One tweet a day on computational mathematics.Peyman Milanfar @docmilanfar
67K Followers 264 Following Distinguished Scientist at Google Research. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.Maxim Raginsky @mraginsky
8K Followers 2K Following father, academic, raconteur, aging wannabe hipster blog: https://t.co/akk6LCvKw6Behnam Neyshabur @bneyshabur
18K Followers 690 Following Senior Staff Research Scientist @GoogleDeepMind, Interested in reasoning w. LLMs, traveling & backpackingBen Recht @beenwrekt
26K Followers 365 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.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)Amin Karbasi @aminkarbasi
8K Followers 2K Following Associate Professor at Yale University, staff research scientist at Google.Dimitris Papailiopoul.. @DimitrisPapail
11K Followers 975 Following prof @ wisconsin; thinking about transformers; learning in context; babas of Inez LilyKyunghyun 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).Lenka Zdeborova @zdeborova
13K Followers 421 Following Professor at EPFL. Une mathémaphysinformaticienne. Passionate mushroom hunter. Tamer of two little dragons.Jason Lee @jasondeanlee
10K Followers 3K Following Associate Professor at Princeton and Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learningAryeh Kontorovich @aryehazan
4K Followers 470 Following probability, statistics, metric spaces, Markov chains, freedom (social & academic), Israel, Jew stuff. opinions represent my employer & all other groups I'm inProf. 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.Soledad Villar @SoledadVillar5
3K Followers 2K Following Applied math/data science/ML Assistant Professor at Johns Hopkins. She/ella. Uruguaya 🇺🇾Gitta Kutyniok @GittaKutyniok
2K Followers 231 Following Bavarian AI Chair for Mathematical Foundations of AI @LMU_Muenchen; Adjunct Professor for ML @UiTromsoBoaz Barak @boazbaraktcs
17K Followers 422 Following Computer Scientist. See also https://t.co/EXWR5k634w, https://t.co/SEVX6it6z3 ( @[email protected] , boaz.barak in threads ). Opinions my own.Tom Goldstein @tomgoldsteincs
23K Followers 2K Following Professor at UMD. AI security & privacy, algorithmic bias, foundations of ML. Follow me for commentary on state-of-the-art AI.Ruilong Li @ruilong_li
665 Followers 216 Following PhD student at @berkeley_ai | Alumni of @GoogleAI, @RealityLabs, @USC_ICT, @Tsinghua_UniKarsten Kreis @karsten_kreis
2K Followers 444 Following Senior Research Scientist at @NVIDIA | Former Physicist | Deep Generative Learning. Opinions are my own.Elisabetta Cornacchia @Elisabetta68885
63 Followers 91 Following Postdoc at MIT in theoretical machine learningGroq Inc @GroqInc
45K Followers 470 Following Creator of the LPU™ Inference Engine, providing the fastest speed for AI applications, designed & engineered in N. America https://t.co/DsEqVAC5DpThomas Scialom @ThomasScialom
6K Followers 232 Following AGI Researcher @MetaAI -- Lead Llama 2 and Postraining Llama 3. Also CodeLlama, Galactica, Toolformer, Bloom, Nougat, GAIA, ..Fabrice NEYRET - pro @FabriceNEYRET
1K Followers 31 Following Google knows everything. Ask NSA for the rest. NB: as for Facebook, I often click "like" just to get a chance to find a post again, not because I approve it.Learning Theory Allia.. @let4all
1K Followers 38 Following Together we will build the future of the machine learning theory research community!Bharath Hariharan @BharathHarihar3
229 Followers 68 Following Assistant Professor @ CS, Cornell University. Computer vision / ML researcherPhilipp Hennig @PhilippHennig5
6K Followers 321 Following Professor for the Methods of Machine Learning at the University of Tübingen.KAIST AI @kaist_ai
1K Followers 169 Following The Kim Jaechul Graduate School of AI at Korea Advanced Institute of Science and TechnologyGeonyeong Park @geonyeong_park
42 Followers 52 Following PhD student @KAIST, BISPL lab & BML lab | Diffusion models, Trustworthy and robust AI, AdaptationProf. Hy Truong Son @sonpascal93
405 Followers 5K Following Tenure-Track Assistant Professor at Indiana State University. Postdoctoral Fellow and Lecturer at UC San Diego. PhD from University of Chicago.Hyungjin Chung @hyungjin_chung
624 Followers 405 Following Ph.D. student @ KAIST | Writer @AlphaSignalAI | Prev- @GoogleAI @ LANL | Diffusion models for inverse problems, AI4ScienceStanford NeuroAI Lab @NeuroAILab
3K Followers 123 Following Neuroscience, artificial intelligence, and psychology research at Stanford University (PI: Dan Yamins)Kento Kawai @kawaisan2000
205 Followers 329 Following Computer Vision / IIM:@Ukita_Lab /MACC:@Matuo_LabVincent Dutordoir @vdutor
999 Followers 650 Following Research Scientist @GoogleDeepMind (AI for Science). Previously: PhD @CambridgeMLG, @SecondmindLabsAyaan Haque @ayaanzhaque
1K Followers 614 Following 20 y/o researcher @LumaLabsAI, @berkeley_ai || learning about learning 💯TTI Ukita Lab. 【豊.. @Ukita_Lab
89 Followers 83 Following 浮田宗伯教授が主宰する豊田工業大学 知能情報メディア研究室です。コンピュータビジョン・画像認識などのマルチメディア計測・認識,および,大規模データの機械学習による計測・認識の高精度化に関する基礎・応用技術を研究しています。Chihiro Nakatani @china64681791
118 Followers 132 Following Ph.D. student at Ukita lab (TTI-J). Machine learning and computer vision for human activity analysis (e.g., sport analysis).Normal Computing 🧠.. @NormalComputing
2K Followers 78 Following We build AI systems that natively reason, so they can partner with us on our most important problems. Join us https://t.co/BcjWCoI5b8.Joe Shenouda @shenouda_joe
113 Followers 152 Following Ph.D. candidate in Electrical and Computer Engineering @ UW-Madison. Interested in machine learning, signal processing and deep learning.Chenlin Meng @chenlin_meng
8K Followers 833 Following Co-founder & CTO @pika_labs | ex @StanfordAILab @StanfordTakahiro Maeda @meaten121
72 Followers 170 Following Doctoral student at @Ukita_Lab of Toyota Technological Institute Japan. Certified Care Worker (介護福祉士) Computer Vision/Robotics Profile: https://t.co/JlZKwkVohiSakana AI @SakanaAILabs
19K Followers 0 Following We are a Tokyo-based R&D company on a quest to create a new kind of foundational AI model based on nature-inspired intelligence. https://t.co/1q07mb3TzEJess Sorrell @JessSorrell
206 Followers 404 Following CS postdoc at Penn. Interested in theory of ML and responsible computing. All cat pictures are my own and do not represent the cats of my employer.Joe Benton @JoeJBenton
248 Followers 63 Following Alignment Science at Anthropic | Previously PhD at University of OxfordMichal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindDurk Kingma @dpkingma
35K Followers 348 Following Deep learning, mostly generative models. Prev. Google Brain/DeepMind, founding team @OpenAI. Inventor of the VAE, Adam optimizer, among other things. ML PhD.Yuxin Chen @chenyx04
189 Followers 187 Following Associate professor of statistics and data science at UPennXingchao Liu @XingchaoL
257 Followers 162 Following PhD Student at UT Austin. Researcher on machine learning.Wuyang Chen @WuyangC
406 Followers 892 Following Ph.D. ECE@UT Austin @utexasece | Postdoc @UCBerkeley | Incoming Asst. Prof. @SFU | Closing the gap b/w DL theory & applications + AI4ScienceGiulio Biroli @GiulioBiroli
1K Followers 38 Following Theoretical Physicist at Ecole Normale Supérieure, Paris France.Bin Yu @bbiinnyyuu
361 Followers 7 Following Professor of Statistics, EECS and Comp. Bio. at UC BerkeleyTim Rocktäschel @_rockt
29K Followers 1K Following Open-Endedness Team Lead @GoogleDeepMind, Professor of AI @AI_UCL, PI @UCL_DARK, @ELLISforEurope Scholar. ex @MetaAI (FAIR), @CompSciOxford. Opinions my own.Shubham Tulsiani @shubhtuls
2K Followers 132 Following Assistant Professor in the Robotics Institute, Carnegie Mellon University I want to build perception systems that can understand the physical worldTobias Uelwer @tuelwer
77 Followers 228 Following Postdoc @TU_Dortmund interested in machine learning and deep learninggalen @galenbrain
79 Followers 367 Following PhD student at UC Berkeley, theoretical neuroscience, vision, ML. The horrors are never-ending yet I remain silly. https://t.co/TdYeYbUChCGowthami Somepalli @gowthami_s
6K Followers 978 Following Grad student @UMDCS. Past: @AIatMeta, @AmazonScience, @IITMadras. Currently working on #Diffusion and #Multimodal understanding. GPU poor. She/her.Katie Bouman @klbouman
4K Followers 0 Following Assistant Professor of CMS/EE @Caltech; Computational Imaging, Computer Vision, and Machine LearningRobert Yang @GuangyuRobert
3K Followers 185 Following Co-founder, CEO at @Altera_AL, Computational Neuroscientist, former Assistant Professor @mitbrainandcog & @MITEECSWhy do diffusion models use the U-Net architecture? Fascinatingly, the U-Net's encoder-decoder structure with long skip connections naturally encodes the belief propagation algorithm for hierarchical models. Explore more in this paper! arxiv.org/abs/2404.18444. .
I'm honored to receive the Amazon Research Award🎉 My group will be exploring how to use LLMs better, guided by principles of information and coding theory. Special thanks to @myhakureimu @yzeng58 and @yingfan_bot, who are already actively engaged in this exciting research 😊
The recipients, representing 51 universities in 15 countries, will have access to Amazon public datasets, AWS AI/ML services and tools, and more. Congrats to the 99 awardees! #AmazonResearchAwards amazon.science/research-award…
😅 The view that GNNs are cool but not super-useful seems somewhat prevalent in the Bay Area 🙃 Parts of the graph ML community now see invariances as unnecessary (note: without them the inputs are sequences not graphs) 🙃 The truth is, GeomDL needs to make a stronger case...🧵
Indeed, graphs are a scam -- an invention from mathematicians to control people! I can prove it -- it is well-known that data is truly i.i.d. (written in all machine learning textbooks). So there exists no relationship between data and graph representation is just an illusion.
We are very excited that our first GH200 nodes have arrived in TACC for our GenAI center. Here is one. Fun facts: NVIDIA makes GH200 'superchips' (i.e. modules), a GH200 DGX box and a GH200 rack, which are all different. As Dan Stanzione, our TACC director, kindly explained…
There's been a lot of discussion on LLMs "memorizing" training data, but we argue for more nuance in the definition of "memorize". This work advocates for adversarial prompts (and whether they can be shorter than the output) as a metric for assessing memorization.
1/What does it mean for an LLM to “memorize” a doc? Exactly regurgitating a NYT article? Of course. Just training on NYT?Harder to say We take big strides in this discourse w/*Adversarial Compression* w/@A_v_i__S @zhilifeng @zacharylipton @zicokolter 🌐:locuslab.github.io/acr-memorizati…🧵
In case you are wondering, this paper proves that, in general, diffusion models do not define optimal transport maps. The proof is not straightforward though (diffusion maps are optimal maps in 1D, for radial measure and for Gaussians ...) cvgmt.sns.it/media/doc/pape…
Robust geometric predicates in #rustlang with #geogram ! As simple as 'cargo add geogram_predicates' Wrapper by Glenn Dittmann New 0.1.5 version has nice demo program, showing what happens with standard floating point numbers: github.com/glennDittmann/… crates.io/crates/geogram…
Those of us old enough to have worked on both "conventional" computer vision & "large scale ML" computer vision are at once awed, elated, and a little pi**ed off to see scale resolve problems we worked on for years. For me it's not the bitter lesson - it's the bittersweet lesson
📢📢Most diffusion (and flow matching) models use handcrafted schedules for their denoising steps during sampling. We show how to optimize them in a principled manner for high-quality generation! @amsabour added quickstart guide & collab to get you started quickly (links below)!
📢📢 Align Your Steps: Optimizing Sampling Schedules in Diffusion Models research.nvidia.com/labs/toronto-a… TL;DR: We introduce a method for obtaining improved sampling schedules for diffusion models, resulting in better samples at the same computation cost. (1/5)
I think people should just go back to using linear models then…
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-…
I am filled with a sense of wonder and admiration when I think about this incredible computer engineering accomplishment of NASA. It is still one of the most fulfilling places to work and my answer when people ask me what I would do if I were not in academia. I experience this…
Amazing that a chip bricked in 46-yr-old Voyager I, preventing it from sending data, and NASA figured out how to split up and reallocate its functions to other hardware, sending code 15 billion miles away (45 hours round trip!)--and Voyager's back online. blogs.nasa.gov/voyager/2024/0…
all the talk about AI recently has reminded me of this lovely & gentle @EmanuelDerman intro to simulated annealing (relevant as an efficient technique to find a closer approximation to a global optima vs a precise local one like with gradient descent) edge.org/response-detai…
Hugging Face is hosting a demo site for @iclr_conf authors to find and claim their papers and discuss those papers on dedicated pages The page includes all accepted papers, along with linked datasets, models, and demos
We started releasing the first chapters of our Geometric Deep Learning book and the accompanying slides from the corresponding Oxford and Cambridge courses.
After 3 years, it's time for us to start sharing the chapters of the GDL book! ❤️ Also included: companion slides from our @Cambridge_Uni & @UniofOxford courses 🧑🎓 Chapter 1 is out **now**! More to follow soon 🎉 geometricdeeplearning.com/book 📖 @mmbronstein @joanbruna @TacoCohen
Daniel Dennett: How to compose a successful critical commentary Rest well, and thank you
@karpathy @danielsateler1 I think some day, projects like PyTorch will make users pay only for the overhead they use. Lots of R&D needed to get there: compiler technology, type systems, various other things. Actually, LuaJIT was really cool in that aspect -- one of the most brilliant pieces of…
I’m excited to announce that in July 2025 I will be joining @UWaterloo as an Assistant Professor in the Department of Statistics and Actuarial Science! Until then, I will continue at Princeton as a DataX Postdoc Fellow, working with Boris Hanin. I have many exciting projects…
💫 Happy to share MoA: a *Mixture-of-Attention* architecture for personalization of generative models! Imagine YOU🫵🏻 drinking boba🧋in a night market, or scuba diving🤿, and more! 📕: arxiv.org/abs/2404.11565 🔗: snap-research.github.io/mixture-of-att… 🎥: youtu.be/Ckv5ttqGJNA