Aäron van den Oord @avdnoord
Research Scientist @ DeepMind avdnoord.github.io/homepage London, England Joined January 2013-
Tweets174
-
Followers13K
-
Following175
-
Likes201
Introducing Udio, an app for music creation and sharing that allows you to generate amazing music in your favorite styles with intuitive and powerful text-prompting. 1/11
Meet Imagen 2: our most advanced text-to-image diffusion technology. ✨ It features high-quality, photorealistic outputs and stronger consistency with your prompts. 🖼 Now available to use via @googlecloud’s #VertexAI platform. → dpmd.ai/x-imagen2
#Lyria is in production and can already used by selected creators on YT Shorts. You can find samples here: youtube.com/hashtag/dreamt…
#Lyria is in production and can already used by selected creators on YT Shorts. You can find samples here: youtube.com/hashtag/dreamt…
Beyond thrilled to share my dream project ever since I got into ML! Have been floored by #Lyria so many times - it's simply on another level 🤯 Humbled by the amazing artists supporting our tech in Dream Track and excited to see how Music AI tools boost musical creativity! 🎶❤️🎤
Beyond thrilled to share my dream project ever since I got into ML! Have been floored by #Lyria so many times - it's simply on another level 🤯 Humbled by the amazing artists supporting our tech in Dream Track and excited to see how Music AI tools boost musical creativity! 🎶❤️🎤
We're starting a new DeepMind research team in California to work on large-scale deep learning models. Apply if you want to contribute to our mission of building AGI!
We're starting a new DeepMind research team in California to work on large-scale deep learning models. Apply if you want to contribute to our mission of building AGI!
Had some fun visualising unconditional text generation process by SUNDAE: dpmd.ai/sundae Text gradually appears from noise by making denoising edits to the whole draft. A lot of impressive samples from image denoising models recently, time for text to catch up? 😀
Autoencoders can generate text well if they learn to correct themselves! Happy to share our new paper SUNDAE: we show how unrolling the autoencoder denoising process during training leads to strong results in machine translation & language modeling. dpmd.ai/sundae 1/3
Autoencoders can generate text well if they learn to correct themselves! With SUNDAE, our team shows how unrolling the autoencoder denoising process during training allows us to achieve strong results in machine translation & language modeling. Paper: dpmd.ai/sundae 1/
Self-supervised learning has made tremendous gains for simple visual tasks like recognizing objects, but interacting with the environment requires detecting, parsing, and understanding their geometry. Contrastive detection greatly facilitates these tasks. dpmd.ai/3jsOV9l
New example showing how to implement a VQ-VAE in #Keras with the PixelCNN part included. The example goes through several key ideas: optimizing discrete latent spaces, codebook sampling, and above all visualizations! keras.io/examples/gener… 1/
New example showing how to implement a VQ-VAE in #Keras with the PixelCNN part included. The example goes through several key ideas: optimizing discrete latent spaces, codebook sampling, and above all visualizations! keras.io/examples/gener… 1/
Honored to have received the MIT TR 35 innovators award. Very grateful to have been able to work with amazing colleagues on this research! @techreview technologyreview.com/innovator/aaro…
MuZero removed simulators in MBRL vs AlphaGo. VQ Models for Planning generalize to partial observable & stochastic environments. How? 1. Discretize states w/ VQVAE 2. Train a LM over states 3. Plan w/ MCTS using the LM Led by @yazhe_li & @sherjilozair arxiv.org/abs/2106.04615
How contrastive learning works on large-scale uncurated data? Want to significantly improve it in such a scenario? Check the new "Divide and Contrast (DnC)" work jointly with @avdnoord and @olivierhenaff ArXiv: arxiv.org/abs/2105.08054
What makes self-supervised learning from uncurated data so challenging? We identified the heavy-tailed distribution of image content as a limiting factor, and address it with Divide and Contrast. Leads to big gains in data-efficient and transfer learning. arxiv.org/abs/2105.08054
Nice use of VQ-VAEs for music generation!
New paper - CURL: Contrastive Unsupervised Representations for RL! We use the simplest form of contrastive learning (instance-based) as an auxiliary task in model-free RL. SoTA by *significant* margin on DMControl and Atari for data-efficiency. arxiv.org/abs/2004.04136
Apparently the models that are shepherding the health of the British people were fed viral pneumonia statistics from a different disease. The arrogance and stupidity of this is terrifying and devastating.
Unsupervised pre-training now outperforms supervised learning on ImageNet for any data regime (see figure) and also for transfer learning to Pascal VOC object detection arxiv.org/abs/1905.09272…
> "AI works like the brain!" Ahh, yes, I fondly remember my intro to linguistics class, wherein I read all of English wikipedia thousands of times until convergence, and then could finally construct better-than-random parse trees.
Soumith Chintala @soumithchintala
185K Followers 877 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Lucas Beyer (bl16) @giffmana
56K Followers 445 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Eric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pKyunghyun 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).Delip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Oriol Vinyals @OriolVinyalsML
166K Followers 82 Following VP of Research & Deep Learning Lead, Google DeepMind. Gemini co-lead. Past: AlphaStar, AlphaFold, AlphaCode, WaveNet, seq2seq, distillation, TF.David Pfau @pfau
22K Followers 1K Following Knowledge manifests itself in radiant dreams that shimmer like the wild sun Views are my own pfau at sigmoid dot social on 🦣 https://t.co/xqtVHHVI17 on 🦋Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistFerenc 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 @BaldertonDmytro Mishkin 🇺�.. @ducha_aiki
18K Followers 591 Following Marrying classical CV and Deep Learning. I do things, which work, rather than being novel, but not working.yobibyte @y0b1byte
15K Followers 2K Following Kurin ViTaly, senior research scientist @IsomorphicLabs, ML PhD from @UniofOxford on RL, Multitask learning & GraphsDanijar Hafner @danijarh
14K Followers 869 Following Building AI that makes autonomous decisions using world models, artificial curiosity, and temporal abstraction @DeepMindSasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzShane Gu @shaneguML
28K Followers 1K Following Research Scientist & Manager @GoogleDeepMind Tokyo/MTV. ex: @GoogleAI Brain, @OpenAI. (JP: @shanegJP)Matthias Niessner @MattNiessner
31K Followers 162 Following Professor for Visual Computing & Artificial Intelligence @TU_Muenchen Co-Founder @synthesiaIONatasha Jaques @natashajaques
25K Followers 1K Following Senior Research Scientist at @GoogleAI and Assistant Professor @uwcse. Social Reinforcement Learning in multi-agent and human-AI interactions. PhD from @MIT.Sara 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.Lilian Weng @lilianweng
94K Followers 148 Following Working on AI safety, past on robotics, applied research @OpenAI; Writing ML blogs to help myself & others to learn; Ideas my own.Paul J. Atzberger @atzberg
102 Followers 887 Following Professor, Mathematics and Mechanical Engineering, University of California Santa Barbara.Mehwish pathani 🌺�.. @mehwish_Pathani
6 Followers 54 Following follow me and get follow back in same timeJuan Hmmm @JuanAH03488233
75 Followers 3K Followingnovice monk @photophagus
55 Followers 3K Following lunarpunk techbro. follow != endorsement of viewsChristopher Wahlen @Christo68497631
0 Followers 1 FollowingCawreo @Cawreo
119 Followers 732 Following Founder & CEO of @NexusNets — e/αi • Testing on: https://t.co/Cso4XFbuKcHenry Bourne @henrybourne_
7 Followers 34 Following PhD student @BristolUniMaths. ₛₑₗբ₋ₛᵤₚₑᵣᵥᵢₛₑₔ ᵣₑₚᵣₑₛₑₙₜₐₜᵢₒₙ ₗₑₐᵣₙᵢₙ₉ բₒᵣ ꜀ₒₙₜᵢₙᵤₐₗₗᵧ ₗₑₐᵣₙᵢₙ₉ ₒₘₙᵢ₋ₒ₆ₛₑᵣᵥᵢₙ₉ ₐGᵢ 🦾Ryan @futuretechdude
26 Followers 97 FollowingArmaan @a_narula48
3 Followers 143 FollowingAsi @Asimoval
7 Followers 319 FollowingChristian Esmann @chrisesmann
165 Followers 1K Following Traveling & Working 🌏 30+ apps developed 📱 Advising startups 🚀Kyra Kadhim @KadhimKyra
67 Followers 126 Following Computational neuroscience PhD student @uni_tue & @MPI_IS. Also veg*, yogi, and some of that hippie stuff💚Pensé FFun @inftyCategory
115 Followers 6K Followingララどり d/age IS.. @presklux49
146 Followers 544 Following シンギュラリタリアン。老化を治療し、永遠の若さを手に入れることを目指しています。老化研究を促進するツールとして、人工知能も重視しています。私の夢は、超知能が管理する色々な箱庭世界で、悠久の時を過ごすことです。Ashley Edwards @ashrewards
483 Followers 200 Following Research scientist @GoogleDeepMind. Past: Uber AI Labs, Georgia TechAryan Pandey (Look fo.. @AryanPa66861306
1K Followers 2K Following Half Machine Learning Engineer || DevOps and Machine Learning || Open Source at OpenVINOcokap79 @cokap7918792
26 Followers 389 FollowingArif Ahmad @ArifAhm92263086
219 Followers 6K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIAli Mohsin Hussain @3black_diamond3
0 Followers 62 FollowingcrystalWen @JackLiuWen
31 Followers 607 Following文博 @lidoyu
6 Followers 354 FollowingMazzystar @immazzystar
2K Followers 368 Following ex-ML engineer, image synthesis/generative model. Free developer, create for fun.郝博阳 @ekaths
14 Followers 338 FollowingAI Generated Producti.. @AIGenPro
552 Followers 2K Following AI Generated Productions LLC is a media company that specializes in high quality entertainment generated by Artificial Intelligence. @AIGenStudios @GenAIChadBerkin Akin @berk1nak1n
5 Followers 98 FollowingJohannes Nørskov Tok.. @RskovToke
1 Followers 50 FollowingAnirudh Sundara Rajan @AniSundar18
4 Followers 54 Following迷途小书童 @smiletoallguys
1 Followers 38 Followingleckie peng @leckiepeng
0 Followers 132 FollowingWei Shi @weishi
54 Followers 934 FollowingXiao Ma @maxiao001
9 Followers 292 Following Research Director @ Temu. Interested in Machine Learning, Recommender Systems, Generative AI, etc. Hiring for talented machine learning engineers!Zizheng Pan @zizhpan
186 Followers 234 Following PhD student @MonashUni | Previous Intern @nvidia and @UniofAdelaideKevin Ly @lifeisscience_5
130 Followers 384 Following PhD Student in Trynka/Lotfollahi lab at @sangerinstitute•@Cambridge_Uni | Former Data & Analytics Specialist @roche_schweiz | MSc Biotechnology @ETHParth Sarthi @parthsarthi03
405 Followers 621 Following Researching Language Models @StanfordNLP, @StanfordAILab Prev: @ContextualAITristan M. Stöber, P.. @tristanstoeber
449 Followers 694 Following computational neuroscientist | speaker and co-founder of @LiSNNinitiative | hippocampus, spiking neural networks, plasticityThinh Le @thinhlpg
1 Followers 13 FollowingThomas Cordier @Notammentmoi
19 Followers 74 FollowingViraj Manwadkar @viraj_manwadkar
66 Followers 384 Following UChicago’22 ; Physics Phd Stanford || he/himSoumith Chintala @soumithchintala
185K Followers 877 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Lucas Beyer (bl16) @giffmana
56K Followers 445 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Oriol Vinyals @OriolVinyalsML
166K Followers 82 Following VP of Research & Deep Learning Lead, Google DeepMind. Gemini co-lead. Past: AlphaStar, AlphaFold, AlphaCode, WaveNet, seq2seq, distillation, TF.David Pfau @pfau
22K Followers 1K Following Knowledge manifests itself in radiant dreams that shimmer like the wild sun Views are my own pfau at sigmoid dot social on 🦣 https://t.co/xqtVHHVI17 on 🦋NeurIPS Conference @NeurIPSConf
111K Followers 35 Following New Orleans, Dec 10-16, 23. https://t.co/ga8aOw615g Tweets to this account are not monitored. Please send feedback to [email protected].Ferenc 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 @BaldertonSergey Levine @svlevine
79K Followers 122 Following Associate Professor at UC Berkeley Co-founder, Physical IntelligenceMatthias Niessner @MattNiessner
31K Followers 162 Following Professor for Visual Computing & Artificial Intelligence @TU_Muenchen Co-Founder @synthesiaIOMax Welling @wellingmax
32K Followers 428 FollowingTim Dettmers @Tim_Dettmers
29K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Lilian Weng @lilianweng
94K Followers 148 Following Working on AI safety, past on robotics, applied research @OpenAI; Writing ML blogs to help myself & others to learn; Ideas my own.Durk Kingma @dpkingma
35K Followers 347 Following Deep learning, mostly generative models. Prev. Google Brain/DeepMind, founding team @OpenAI. Inventor of the VAE, Adam optimizer, among other things. ML PhD.Taco Cohen @TacoCohen
21K Followers 3K Following Deep learner at FAIR. Into codegen, equivariance, generative models. Spent time at Qualcomm, Scyfer (acquired), UvA, Deepmind, OpenAI.Nando de Freitas 🏳.. @NandoDF
97K Followers 658 Following I research intelligence to understand what we are, and to harness it wisely. I lead a wonderfully creative AI team at @GoogleDeepMind who inspire me everyday.rohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.Ben Poole @poolio
17K Followers 1K Following research scientist at google brain. phd in neural nonsense from stanford.SynthLabs @synth_labs
12K Followers 43 Following AI Aligned with Your Vision. We’re doing cutting edge research for transparent, auditable AI alignment.Alex Mordvintsev @zzznah
16K Followers 2K Following Mad Scientist, DeepDream creator. Designing Self-Organising Systems and Programmable Artificial Life. https://t.co/rntipHzHW3Colin Raffel @colinraffel
30K Followers 654 Following nonbayesian parameterics, sweet lessons, and random birds. Friend of @srush_nlpHanne Van Briel @hanne_van_briel
9K Followers 2K Following Visual AI Educator.Consultant || Artist (AI + abstract painting + photography) Former Sr Product Mngr, Data @ Internat. Marketing Automation PlatformTwelve Labs (twelvela.. @twelve_labs
2K Followers 132 Following 🎥 Building multimodal foundation models for video understanding: https://t.co/iKo4kmNv6p 👉 Curate a community of Multimodal Minds: https://t.co/VUakXlagBOBojan Tunguz @tunguz
187K Followers 8K Following Machine Learning ex Nvidia. Kaggle Quadruple Grandmaster. Data Scientist. Physicist. Catholic. Husband. Father. Stanford Alum. e/xgb. XGBoost.eth. AMDG.Yaroslav Ganin @yaroslav_ganin
4K Followers 230 Following Co-Founder @udiomusic. Research Scientist. Previously: @DeepMindAI, Mila (Montréal, Canada), Skoltech (Moscow, Russia). Views are my own.Ed Newton-Rex @ednewtonrex
7K Followers 1K Following CEO of @fairlytrained / Composer. Previously founded Jukedeck, VP Audio at Stability AI.udio @udiomusic
27K Followers 0 FollowingPatrick Esser @pess_r
5K Followers 297 Following Walking on the generative side of computer vision. he/himMidjourney @midjourney
338K Followers 0 Following New research lab. Exploring new mediums of thought. Expanding the imaginative powers of the human species. Join our beta: https://t.co/yAUpCWJRziReid Southen @Rahll
13K Followers 2K Following 🎬 Film concept artist and illustrator. 🎞️ Marvel, DC, Matrix, Alien, Transformers, The Woman King, Jupiter Ascending, The Hunger Games.James Bradbury @jekbradbury
11K Followers 8K Following Compute at @AnthropicAI! Previously JAX, TPUs, and LLMs at Google, MetaMind/@SFResearch, @Stanford Linguistics, @Caixin.Quanquan Gu @QuanquanGu
9K Followers 2K Following Professor @UCLA | Head of AIDD, ByteDance Research | Recent work: Self-play fine-tuning (SPIN) | Opinions are my ownDavid Ding @DavidDingAI
2K Followers 121 Following CEO and co-founder of @udiomusic. ex Google DeepMindKeunwoo Choi @keunwoochoi
6K Followers 800 Following AI x {LLM Engineer @PrescientDesign @genentech, Advisor @gaudiolab}. music, audio, language, AI. Prev: @BytedanceTalk, @spotify, @c4dm @qmul.xAI @xai
997K Followers 36 FollowingFinster AI @finsterai
283 Followers 21 Following Building AI agents that integrate disparate sources of financial and market data. Founded by an ex DeepMind and JP Morgan team. Backed by @HoxtonVentures.Ostris @ostrisai
1K Followers 146 Following AI / ML researcher and developer. Forcing rocks to think since 1998.Mikhail Parakhin @MParakhin
17K Followers 21 FollowingSid Jayakumar @sidfix
1K Followers 1K Following Founder @finsterai, trying to 10x financial knowledge work. Previously AI researcher @GoogleDeepMind, @QueensCam, @UCL. Angel https://t.co/zsqm77gOjw.Susan Zhang @suchenzang
20K Followers 504 Following @ Google Deepmind. Past: @MetaAI, @OpenAI, @unitygames, @losalamosnatlab, @Princeton etc. Always hungry for compute.Ideogram @ideogram_ai
39K Followers 0 Following Helping people become more creative. It's pronounced eye-diogram. Join our lovely community at https://t.co/aKDNl4OOQf.Ammaar Reshi @ammaar
39K Followers 1K Following Head of Design @elevenlabsio // Prev. @brexhq, @PalantirTech // Exploring AI and sharing learnings • 🇵🇰typedfemale @typedfemale
23K Followers 479 Following a really exciting new account "have you ever though you might be like scott alexander? very smart, but can't do math" - anonRobin Rombach @robrombach
6K Followers 397 Following Generative enthusiast and long-term PhD Student @LMU_Muenchen. Author of VQGAN, Latent Diffusion, Stable Diffusion.Dilip Krishnan @dilipkay
755 Followers 61 Following https://t.co/eJ1xsnaAff Working on next-gen LLM's @ GoogleNick St. Pierre @nickfloats
156K Followers 2K Following Creative Director and unofficial Midjourney shill. Publicly exploring AI & sharing learnings.George Hotz 🌑 @realGeorgeHotz
248K Followers 172 Following President @comma_ai. Founder @__tinygrad__Pabolo @PaboloAi
127 Followers 6 Following Your all-in-one AI movie creation tool 🤖 Revolutionizing the world of story telling 🎥 Startup 🚀 #text2movie #AIMovieJulie W. Design @juliewdesign_
31K Followers 549 Following creating visual narratives with traditional and generative-AI tools, specializing in graphic design, post-photography and storytellingDavid @DavidSHolz
53K Followers 5K Following founder @midjourney, prev founder leap motion, nasa, max planckJοοsτ @jarnoudt
237 Followers 182 Following I lead attribution @twitter. ex Google. in Brooklyn. from 🇧🇪. mostly lurkingJoe Penna @MysteryGuitarM
196K Followers 2K Following Film director. Recovering YouTuber. Once "MysteryGuitarMan". Now: Director of ARCTIC (2019) and STOWAWAY (2022) — Producer of WOMAN OF THE HOUR (coming soon)DeepFloyd @deepfloydai
8K Followers 24 Following DeepFloyd AI Research Band; working with @StabilityAI ❤️ https://t.co/ttswCIcnmZJohannes Stelzer @j_stelzer
558 Followers 551 Following Gen AI / Closed Loop Systems / Digital Therapeutics. Senior ML Scientist at Champalimaud Center for the Unknown @Neuro_CFPerplexity @perplexity_ai
131K Followers 28 Following World's first conversational answer engine. Get our iOS and Android app: https://t.co/BBZ1kG0TVGfabian (glif/acc) @fabianstelzer
18K Followers 4K Following building https://t.co/GVc2KGouz6 / @heyglif - an all prompts / no code AI sandbox. prompts at @SALT_VERSE (season 2 in the works!)Excited to be launching udio at long last! 1/6
Introducing Udio, an app for music creation and sharing that allows you to generate amazing music in your favorite styles with intuitive and powerful text-prompting. 1/11
Dishoom, King’s Cross, is a favorite for Google Deepminders. That’s also where I had my farewell lunch in 2019. Yum.
The best thing about London is the Indian food
This is mind-blowing technology, I played with it for hours when I got my hands on it! Huge congrats to Aaron and the team!
@lyria is finally out! Very proud of my team and the technology we have built. Probably the coolest project I've ever worked on and super excited that we are releasing Lyria in partnership with artists and the music industry!
#Lyria is a big leap forward in music generation! Currently running in a trialled YT experiment 'Dream Track'. Congratulations to @avdnoord and team 🎚️🎙️🎼🎶 youtube.com/hashtag/dreamt…
@lyria is finally out! Very proud of my team and the technology we have built. Probably the coolest project I've ever worked on and super excited that we are releasing Lyria in partnership with artists and the music industry!
Excited that this is out! When Kazuya and I started training the first versions of this model last year, we had no idea that it would turn out this good, the progress that the team has made in the last year was incredible. Thanks @avdnoord for being a fantastic team lead!
Thrilled to share #Lyria, the world's most sophisticated AI music generation system. From just a text prompt Lyria produces compelling music & vocals. Also: building new Music AI tools for artists to amplify creativity in partnership w/YT & music industry deepmind.google/discover/blog/…
🦩😎
The year is 2032. A model was trained on all images, videos and text on the web, using over 100 yottaFLOPs. It still thinks this is an image of a dog. To fix models post-hoc, check out PAINT!🎨 📜 arxiv.org/abs/2208.05592 💻 github.com/mlfoundations/… 🌐 model-patching.github.io
We're starting a new DeepMind research team in California to work on large-scale deep learning models. Apply if you want to contribute to our mission of building AGI!
Interested in exploring the limits of large-scale models? Consider joining our brand new Scalable Deep Learning team in California as a Research Engineer or Research Scientist, see job descriptions below! boards.greenhouse.io/deepmind/jobs/… boards.greenhouse.io/deepmind/jobs/…
Excited to share our latest work describing a new approach to lossy compression: ✨DiffC✨ sends an image corrupted by Gaussian noise which is then denoised by the receiver. Surprisingly, this simple approach works well despite operating in pixel space...
I am happy to report that our paper on "Algorithms for the Communication of Samples" has been accepted to ICML 2022. This problem frequently crops up in neural compression but also in differential privacy. arxiv.org/abs/2110.12805
@ilyasut Here is an idea: Ilya is becoming a philosopher.
Diffusion-based generative models are SOTA on perceptual quality, but how good are they at density estimation? Very good it turns out! 📢Announcing our new paper on diffusion models, with SOTA likelihoods & compression + new theoretical insights into this exciting model class.
New paper: Variational Diffusion Models (VDMs)! arxiv.org/abs/2107.00630 ✅ New general insights into diffusion models ✅ Simple objective ✅ Fast optimization & anytime synthesis ✅ SotA likelihoods & lossless compression Work with @TimSalimans @poolio @hojonathanho (1/n)
@avdnoord @techreview Congratulations Aäron! Hearing that voice in 2016 was astounding, and it is incredible to see how quickly WaveNet voice became a standard in the industry.
Congrats Aaron, very well deserved!
Honored to have received the MIT TR 35 innovators award. Very grateful to have been able to work with amazing colleagues on this research! @techreview technologyreview.com/innovator/aaro…
This is super well deserved. The article doesn’t even mention all the other amazing work Aäron has done (PixelCNN, VQ-VAE, the list goes on)
Honored to have received the MIT TR 35 innovators award. Very grateful to have been able to work with amazing colleagues on this research! @techreview technologyreview.com/innovator/aaro…