Yang Song @DrYangSong
Leading the Strategic Explorations team @OpenAI. Score-Based Models. Diffusion Models. Consistency Models. yang-song.net Stanford, CA Joined July 2014-
Tweets201
-
Followers10K
-
Following885
-
Likes1K
🚀Our latest blog post unveils the power of Consistency Models and introduces Easy Consistency Tuning (ECT), a new way to fine-tune pretrained diffusion models to consistency models. SoTA fast generative models using 1/32 training cost! 🔽 Get ready to speed up your generative…
Fast sampling with 'Multistep Consistency Models': We get 1.6 FID on Imagenet64 in 4 steps and scale text-to-image models, generating 256x256 images with 16 steps. Guess which row is distilled? With @emiel_hoogeboom @TimSalimans Arxiv: arxiv.org/abs/2403.06807
Announcing Score Entropy Discrete Diffusion (SEDD) w/ @chenlin_meng @StefanoErmon. SEDD challenges the autoregressive language paradigm, beating GPT-2 on perplexity and quality! Arxiv: arxiv.org/abs/2310.16834 Code: github.com/louaaron/Score… Blog: aaronlou.com/blog/discrete-… 🧵1/n
Super excited to announce our new work: Synthesizing Moving People with 3D Control (3DHM)💡 Why is 3DHM unique? With 3D Control, 3DHM can animate a 𝗿𝗮𝗻𝗱𝗼𝗺 human photo with 𝗮𝗻𝘆 poses in a 𝟯𝟲𝟬-𝗱𝗲𝗴𝗿𝗲𝗲 camera view and 𝗮𝗻𝘆 camera azimuths from 𝗮𝗻𝘆 video!
Today is a new day and a new blog post on score-based generative models. How do we use score matching to learn generative models defined by a stochastic/ordinary differential equation? Check this out! Post: jmtomczak.github.io/blog/17/17_sbg… Code: github.com/jmtomczak/intr…
New year, new blog posts! Today, I start with the first post from a series on score-based generative models. Are you curious about score matching and how to implement it? Check this out! Post: tinyurl.com/4jzmbehy Code: tinyurl.com/yw954a9b
CCM: Adding Conditional Controls to Text-to-Image Consistency Models paper page: huggingface.co/papers/2312.06… Consistency Models (CMs) have showed a promise in creating visual content efficiently and with high quality. However, the way to add new conditional controls to the…
The first Consistency Model for Video was just released! 🤯 It enables video generation with as little as 4 sampling steps: generating 16 frames (at 256x256 resolution) takes 10 seconds only! So not real-time yet (as for images), but close! More details below! ⬇️⬇️
I'll be at #NeurIPS2023, and the academic job market this year! RT will be greatly appreciated! I work on statistics and information theory, with applications in robust statistics, offline RL, game theory, human-AI interactions and LLMs. I'm recently working on better…
Thanks @kenrickcai from @Forbes for covering our story! forbes.com/sites/kenrickc…
There exists no sentence in any language that conveys how happy I am:
There exists no sentence in any language that conveys how happy I am:
Was excited to join @OpenAI for its scientific achievements, but now even more for its people. The love of folks for one another and efforts to save the company is like nothing I’ve seen before. Talking science with @ilyasut has been joy & privilege. Looking forward to more! ❤️
i love openai, and everything i’ve done over the past few days has been in service of keeping this team and its mission together. when i decided to join msft on sun evening, it was clear that was the best path for me and the team. with the new board and w satya’s support, i’m…
Amazing progress made today. We will come back stronger & more unified than ever:
Amazing progress made today. We will come back stronger & more unified than ever:
We explored Jacobi iteration for accelerating sequential computation in a previous work (arxiv.org/abs/2002.03629), with success in PixelCNN decoding, DenseNet evaluation, and RNN training. It's gratifying to see that an improved method can now significantly speed up LLM decoding.
We explored Jacobi iteration for accelerating sequential computation in a previous work (arxiv.org/abs/2002.03629), with success in PixelCNN decoding, DenseNet evaluation, and RNN training. It's gratifying to see that an improved method can now significantly speed up LLM decoding.
ChatGPT with voice is now available to all free users. Download the app on your phone and tap the headphones icon to start a conversation. Sound on 🔊
Over the last few months I have spent a lot of time sampling from this model. Some tips: 1) You can generate videos even with small GPUs (just decrease number of frames you decode at a time as this eats most VRAM). 14 frames (decoding one at a time) should be less than 20GB VRAM
Over the last few months I have spent a lot of time sampling from this model. Some tips: 1) You can generate videos even with small GPUs (just decrease number of frames you decode at a time as this eats most VRAM). 14 frames (decoding one at a time) should be less than 20GB VRAM
New results just dropped. Check out our new, fast decoding algorithm -- lookahead decoding!
New results just dropped. Check out our new, fast decoding algorithm -- lookahead decoding!
Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Kevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistRosanne Liu @savvyRL
33K Followers 968 Following Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS. Writing https://t.co/IbycyGfnDREric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pProf. 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.Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Arash Vahdat (hiring) @ArashVahdat
8K Followers 806 Following Principal scientist and research manager @nvidia research, leading forward-looking fundamental generative AI research efforts, views are my own.Durk 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.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)Shane Gu @shaneguML
28K Followers 1K Following Research Scientist & Manager @GoogleDeepMind Tokyo/MTV. ex: @GoogleAI Brain, @OpenAI. (JP: @shanegJP)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.Ben Poole @poolio
17K Followers 1K Following research scientist at google brain. phd in neural nonsense from stanford.Jascha Sohl-Dickstein @jaschasd
19K Followers 625 Following Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.Yuandong Tian @tydsh
16K Followers 806 Following Research Scientist and Senior Manager in Meta AI (FAIR). AI-guided Optimization and Representation Learning. Novelist in spare time. PhD in @CMU_Robotics.rohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.Animesh Garg @animesh_garg
21K Followers 1K Following Foundation Models for Generalizable Autonomy. Assistant Professor in AI Robotics @GeorgiaTech + @NvidiaAI. prev @Stanford @berkeley_ai @UofTCompSciJiaming Song @baaadas
5K Followers 992 Following Chief Scientist @LumaLabsAI. Working on visual generative AI. Were @NVIDIA @Stanford @OpenAI @MetaAIKyle Cranmer @KyleCranmer
16K Followers 3K Following Director Data Science Institute @UWMadison @datascience_uw. EiC @MLSTjournal. Physics, stats/ML/AI, open science. same handle @sigmoid.social and bskySam Power @sp_monte_carlo
17K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. (he / him)Yangming Li @li_yangming
8 Followers 73 Following박민철 @nogangking
0 Followers 2 FollowingDmitry Lyalin @LyalinDotCom
9K Followers 6K Following Product @ Google | Firebase serverless lead (web, compute, storage & AI & ML). Previously product @MSFT | 24+ years in tech .. dev, PMM, PM Opinions are my ownzy_zhao @zhao_zy44927
35 Followers 62 FollowingJanhavee Shinde @SJanhavee
58 Followers 2K FollowingROM @ROM_DPP
75 Followers 152 Followingbizika @bizika7
22 Followers 380 Followinghualianmaozi @hualianmaozi
4 Followers 53 FollowingTuan Tran Anh @anhtuanhsgs
18 Followers 130 Followingtiood @justfnni
0 Followers 27 FollowingLinglingzhi Zhu @lzzhuling
9 Followers 161 FollowingKarl @tomatoxuhs
32 Followers 461 FollowingBingzheng @weibingzheng
40 Followers 137 FollowingIvan @ivan_7707
81 Followers 725 FollowingSwetha Magesh @swetha__magesh
15 Followers 60 FollowingIsaac Oduro @IOduro43136
2 Followers 16 FollowingEtrit Haxholli @etrit_haxholli
2 Followers 17 FollowingYuanbo Yang @YuanboYang60742
12 Followers 179 FollowingZongcheng Wang @zcwang1222
6 Followers 276 FollowingMichael Malek @mikegmalek
13 Followers 181 FollowingRong Yiming @RongYiming
29 Followers 26 FollowingHaolin Liu @hlinliu
130 Followers 550 Following Ph.D. candidate at CMU (@CarnegieMellon) | Working on additive manufacturing technologies & materials scienceHypocritis @Hypocritis_Sun
10 Followers 68 FollowingWang Fu @fuwangoo
4 Followers 46 Followingstellalalalandbj @stellalala12185
5 Followers 117 FollowingJonas Eichinger @JfE88
33 Followers 275 FollowingSunqi Fan @Sunqi_Fan
111 Followers 586 Following a third-year undergrad @Tsinghua_Uni, studying NLP/LLM/CV. Seeking for 25 Fall Ph.D. positionwo7fwto66ax9ac @cy0ju7pzm5icee
4 Followers 392 Following The team offers short-term investments in cryptocurrencies. With a rigorous plan, you can earn between $500 and $5,000. Click to join TG: https://t.co/v8zYH6756YBergen & Associates @BergenandAssoc
18 Followers 265 FollowingMike Qi @MikeQi59893881
5 Followers 519 FollowingVikram Dutt @vd_
834 Followers 7K FollowingAlexandra Wernersson @astro_alexus
4 Followers 44 Following PhD student in Physics at the University of Amsterdam. Gravitational waves+machine learning+cosmologyBuran Liu @BuranLiu101
1 Followers 46 FollowingKiefer @pam_redd5372
1 Followers 1K FollowingPeter Kim @tspeterkim
34 Followers 82 FollowingPensé FFun @inftyCategory
100 Followers 6K FollowingChia Hong Hsu @ch_dinocat35
5 Followers 11 FollowingTaishi @Setuna7777_2
2K Followers 3K Following CS M1 at @tokyotech_jp advised by @rioyokota 未踏TG23 Research intern: @SakanaAILabsYi 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.Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Kevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistLucas Beyer (bl16) @giffmana
56K Followers 447 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Jia-Bin Huang @jbhuang0604
51K Followers 285 Following Associate Professor @umdcs; Part-time Research Scientist @Meta. I like pixels.Rosanne Liu @savvyRL
33K Followers 968 Following Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS. Writing https://t.co/IbycyGfnDREric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pProf. 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.Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).NeurIPS Conference @NeurIPSConf
112K 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].Horace He @cHHillee
23K Followers 449 Following Working at the intersection of ML and Systems @ PyTorch "My learning style is Horace twitter threads" - @typedfemaleGautam Kamath @thegautamkamath
44K Followers 507 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Co-EiC @TmlrOrg. I lead @TheSalonML. Privacy, robustness, machine learning.Arash Vahdat (hiring) @ArashVahdat
8K Followers 806 Following Principal scientist and research manager @nvidia research, leading forward-looking fundamental generative AI research efforts, views are my own.Durk 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.Behnam Neyshabur @bneyshabur
18K Followers 690 Following Senior Staff Research Scientist @GoogleDeepMind, Interested in reasoning w. LLMs, traveling & backpackingDan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)Yi Tay @YiTayML
29K Followers 97 Following chief scientist / cofounder @RekaAILabs 🫠 past: research scientist @google brain 🤯 currently learning to be a dad 🍼Eric Wallace @Eric_Wallace_
6K Followers 1K Following Researcher at OpenAI working to make language models more trustworthy, secure, and private.Kavin Karthik @KavinIK
1K Followers 1K Following Member of Technical Staff at OpenAI. Ex - Google and IIT Madras AlumVolodymyr Kyrylov @darkproger
2K Followers 2K Following AI student at USI/ETH. Donate https://t.co/GDSkWG2takJonathan Heek @JonathanHeek
234 Followers 5 FollowingMarco Pavone @drmapavone
3K Followers 64 Following Prof @Stanford, Distinguished Research Scientist and AV research lead @nvidia. PhD from @MITAeroAstro. Robotics, autonomous systems, AI. Opinions are my own.Mistral AI @MistralAI
90K Followers 0 Following Fast, open-source and secure language models. Join us https://t.co/INALdNGvCPJosh Susskind @jsusskin
2K Followers 538 Following Apple ML research: foundations, perception, action, future technology, creativity, curiosity, compositionality, scientific jazz!Katerina Fragkiadaki @KaterinaFragiad
283 Followers 48 Following Associate Professor @CMU working on #AI #ComputerVision #Robotics #LanguageGroundingEric Schmidt @ericschmidt
2.2M Followers 224 Following Former Executive Chairman & CEO and tweets from Schmidt FoundationDanielle Belgrave @DaniCMBelg
7K Followers 2K Following VP of AI/ML @GSK. Curious about using AI to make the world a better place. Views my own.Hattie Zhou @oh_that_hat
5K Followers 765 Following Finding \hat{y} Give me anonymous feedback: https://t.co/7aBNrpbad8Ashwini Pokle @ashwini1024
271 Followers 434 Following PhD student at CMU (@mldcmu). Prev. @Stanford, @bitspilaniindia | interested in generative models and deep equilibrium modelsAshish Vaswani @ashVaswani
19K Followers 2K FollowingHyung Won Chung @hwchung27
18K Followers 231 Following Research Scientist @OpenAI. Past: @Google Brain / PhD @MITfforres @fforres
5K Followers 5K Following Human Data @OpenAI - Doin @JSconfCL & @JavaScriptChile. Lovin' Frontend Infrastructure, JS, DX, TS — @_pilliin_'s husband — he/him — Living with ADHD ❤️Subbarao Kambhampati .. @rao2z
16K Followers 29 Following AI researcher & teacher @SCAI_ASU. Works on Human-Aware AI. Former President of @RealAAAI; Chair of @AAAS Sec T. Here to tweach #AI. YouTube Ch: https://t.co/4beUPOmMW6Jiahui Yu @jhyuxm
2K Followers 777 Following Member of Technical Staff @OpenAI; previously Research Scientist at Google Brain/DeepMind.Jitendra MALIK @JitendraMalikCV
4K Followers 0 FollowingJacob Hilton @JacobHHilton
391 Followers 33 FollowingYutong Bai @YutongBAI1002
3K Followers 397 Following EECS Rising Star, 2023 Apple Scholar, Visiting PhD @berkeley_ai, Intern @GoogleAI Brain team @MetaAI (FAIR Labs), CS PhD @JHUCompSciYaron Lipman @lipmanya
3K Followers 399 Following Faculty at @WeizmannScience, research scientist @MetaAI (FAIR). Interested in deep learning of irregular/geometric data and generative models.🎗️Demi Guo @demi_guo_
22K Followers 694 Following Co-founder & CEO @pika_labs | ex @StanfordAILab @HarvardBanghua Zhu @BanghuaZ
2K Followers 804 Following PhD @Berkeley_EECS, statistics, info theory, LLM, RL, Human-AI Interactions.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/YtGtDh1aAVBret Taylor @btaylor
139K Followers 2K Following Co-Founder @SierraPlatform. Board @OpenAI @Shopify.Boyang Niu @kumquatexpress
981 Followers 194 Following Engineering @openai, @southpkcommons fellowship, formerly @Dropbox @Square 2x startupEmilian Postolache @EmilianPostola1
404 Followers 611 Following Research Fellow @CaFoscari, Ph.D. student in CS @SapienzaRoma | Former @SonyCSL, @Dolby and @c4dm | Amateur DJJong Wook Kim 💟 @_jongwook_kim
4K Followers 467 Following Member of Technical Staff @OpenAI, authored CLIP and Whisper; previously at @nyuMARL, @SpotifyResearch, @pandoramusic, @kakaocorpglobal, and @NCSOFTKevin Scott @kevin_scott
28K Followers 692 Following Chief Technology Officer @Microsoft; Host of #BehindTheTech podcast https://t.co/05oKfZqU3e; Author of "Reprogramming the American Dream"Joshua Achiam ⚗️ @jachiam0
14K Followers 948 Following Human. Trying to make safe alchemy machines. Thinking about humanist alchemism (h/alc ⚗️, maybe). Main author of https://t.co/cKuSh210l1lmsys.org @lmsysorg
37K Followers 172 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/IDFeIDIOtmAlexis Conneau @alex_conneau
24K Followers 113 Following Audio AGI Research Lead @OpenAI - GPT-Next - Past: XLM, Unsupervised ASR, Unsupervised MT, Wav2vec 2.0/XLSR, MUSE, Unsupervised cross-lingual transferJames Betker @neonbjb
2K Followers 6 FollowingWenlei Xie @torch_wx
1K Followers 67 Following Retrieval & Search @OpenAI. Prev tech lead in @PyTorch and @prestodb. Engineering leadership, research taste, hacking when necessary. Opinions my own.Cheng Lu @ChengLu05671218
1K Followers 85 Following Member of technical staff @OpenAI. PhD @Tsinghua_Uni. Interested in diffusion models.Evan Morikawa @E0M
13K Followers 1K Following Manage eng at @openai. Building GPT-4, ChatGPT, DALL·E, Codex, & GPT-3 APIs. Prev: Dir Eng @Nylas, Co-Founder @Proximate, @OlinCollege alum.There is a really nice community of researchers developing transformer alternatives. Want to highlight these impressive folks. Simran Arora (@simran_s_arora), Chunting Zhou (@violet_zct), Dan Fu (@realDanFu), and Songlin Yang (@SonglinYang4)
More work coming up & we are hiring: openai.com/careers/search…
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details: arxiv.org/abs/2404.13208
I'm writing my PhD thesis. The major influences over the past 3 years came from 3 papers: 1. Towards Causal Representation Learning. 2. Deep Structural Causal Models for Tractable Counterfactual Inference. 3. Score-Based Generative Modeling through Stochastic Differential…
This was a fun project! If you could train an LLM over text arithmetically compressed using a smaller LLM as a probabilistic model of text, it would be really good. Text would be represented with far fewer tokens, and inference would be way faster and cheaper. The hard part is…
Ever wonder why we don’t train LLMs over highly compressed text? Turns out it’s hard to make it work. Check out our paper for some progress that we’re hoping others can build on. arxiv.org/abs/2404.03626 With @blester125, @hoonkp, @alemi, Jeffrey Pennington, @ada_rob, @jaschasd
Life update! In the fall I'll start as a Junior Fellow at the Society of Fellows at @Harvard and an @iaifi_news fellow at MIT. Looking forward to new adventures with folks across @KempnerInst @hseas @MITMath and @Harvardphysics. Please reach out if/when you're in Cambridge 🙂.
I’m super proud of my PhD advisee @msalbergo. He has had such an impressive and diverse string of papers driven by intellectual curiosity and a sense of style that has developed and matured over the last few years. Congratulations Michael!
Life update! In the fall I'll start as a Junior Fellow at the Society of Fellows at @Harvard and an @iaifi_news fellow at MIT. Looking forward to new adventures with folks across @KempnerInst @hseas @MITMath and @Harvardphysics. Please reach out if/when you're in Cambridge 🙂.
This blog post is an amazing exposition and analysis of consistency models, and how they relate to diffusion models, leading to several suggested improvements to the training procedure that look very promising. Definitely worth a read!
🚀Our latest blog post unveils the power of Consistency Models and introduces Easy Consistency Tuning (ECT), a new way to fine-tune pretrained diffusion models to consistency models. SoTA fast generative models using 1/32 training cost! 🔽 Get ready to speed up your generative…
🚀Our latest blog post unveils the power of Consistency Models and introduces Easy Consistency Tuning (ECT), a new way to fine-tune pretrained diffusion models to consistency models. SoTA fast generative models using 1/32 training cost! 🔽 Get ready to speed up your generative…
I'm thrilled to be a part of @AsariAILabs. Our goal is to design AI systems that can break down problems, discover new abstractions, reason about their correctness (and what notions of correctness are required), and generally plan at multiple levels of granularity. These…
A new journey begins – 🚀 we’re excited to launch! Our mission is to build AI that helps us co-invent the future. -- And we’re hiring to make this happen👇 We’re building a new type of AI agent and tools that help us imagine and create 10x better solutions, products, and…
Congrats to @ScottWu46 @WuNeal @ecnerwala @stevenkplus1 @walden_yan and team on launching Devin! It's a really exciting glimpse into the future of coding with AI, with the strongest technical founding team in the last 5 years!
Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is…
Want to sample fast from diffusion models? Check out our work on multistep consistency. It turns out that training consistency models over multiple sections is much easier than over one big one. Even I can do it. For more detail see thread below (1/7)
Fast sampling with 'Multistep Consistency Models': We get 1.6 FID on Imagenet64 in 4 steps and scale text-to-image models, generating 256x256 images with 16 steps. Guess which row is distilled? With @emiel_hoogeboom @TimSalimans Arxiv: arxiv.org/abs/2403.06807
This paper essentially unifies TRACT (arxiv.org/abs/2303.04248, @D_Berthelot_ML et al.) and Consistency Models (arxiv.org/abs/2303.01469, @DrYangSong). Basically bring together a few simple elements that work really well together. For more details check out our paper.
Fast sampling with 'Multistep Consistency Models': We get 1.6 FID on Imagenet64 in 4 steps and scale text-to-image models, generating 256x256 images with 16 steps. Guess which row is distilled? With @emiel_hoogeboom @TimSalimans Arxiv: arxiv.org/abs/2403.06807
Announcing Score Entropy Discrete Diffusion (SEDD) w/ @chenlin_meng @StefanoErmon. SEDD challenges the autoregressive language paradigm, beating GPT-2 on perplexity and quality! Arxiv: arxiv.org/abs/2310.16834 Code: github.com/louaaron/Score… Blog: aaronlou.com/blog/discrete-… 🧵1/n
Awesome work by @SaberaTalukder 🥳🥳 It's so hard to navigate the model design space. Discrete tokenization for times series modeling FTW!
Tokenization (aka the root of suffering, iykyk) has gotten a terrible rap this past week😅 but in nascent fields this rap is wack🌶️ I am ecstatic to share➡️TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis TOTEM learns discrete time tokens (not patches!!)
Such an awesome project that combines diffusion models, symbolic musical rule guidance, and stochastic control! scg-rule-guided-music.github.io This one is my favorite (musical rules based on vertical note density, horizontal note density, chord progression): youtube.com/watch?v=HZoQj2…
Excited to share our work on symbolic music generation: arxiv.org/abs/2402.14285! We introduce a symbolic music generator with non-differentiable rule guided diffusion models, enabling musicians to effectively use it as a compositional tool. Website: scg-rule-guided-music.github.io. 🧵👇
We are excited to share Large World Model (LWM), a general-purpose 1M context multimodal autoregressive model. It is trained on a large dataset of diverse long videos and books using RingAttention, and can perform language, image, and video understanding and generation.
Cheers to the best valentine I could ask for.
Happy Chinese New Year! Wish everyone good fortune in 2024, year of loong!