Yuming DU
@yuming_du
Followers
933
Following
732
Statuses
77
Research Scientist at @Meta GenAI. | PhD in Computer Vision @ImagineEnpc | Opinions are my own
Zurich
Joined February 2020
Our team is look for interns working on cutting-edge image/video synthesis models. Join us at Meta GenAI Zürich! You can also send you CV to my email: dym@meta.com
📢Now Hiring: PhD Interns at @Meta! 🔍 We're on the hunt for exceptional candidates to intern with our team and work on cutting-edge #DiffusionModels at Meta - GenAI. 💡 Apply Now:
2
12
115
RT @rsumbaly: When we wrote the first research proposal for Movie Gen 6 months back we had two goals in mind: 🎬 First, accelerate creative…
0
2
0
RT @AlbertPumarola: We can finally share "Movie Gen" 🥳: * 30B video model, 73K video context tokens. * T2V: 16s video generation at 1080p.…
0
19
0
RT @rsumbaly: Lights, camera, action - introducing Meta's Movie Gen! Our latest breakthrough in AI-powered media generation, setting a new…
0
10
0
RT @Ahmad_Al_Dahle: With today’s launch of our Llama 3.1 collection of models we’re making history with the largest and most capable open s…
0
229
0
0
0
2
Fabulous work from my amazing teammates at Meta! Try it out on your diffusion models!
Diffusion models are often prohibitively slow. 😢 In our #CVPR2024 paper "Accelerating Diffusion Models through Block Caching", we present a technique to make SOTA models like LDM up to 1.8x faster without sacrificing quality.🚀 Check out our video here:
0
0
4
RT @felixwimbauer: Diffusion models are often prohibitively slow. 😢 In our #CVPR2024 paper "Accelerating Diffusion Models through Block Ca…
0
53
0
LumaAI's text2video generation model does not do security check🤣🤣🤣You might want to be careful with your prompts..
0
0
6
@chriswolfvision @giffmana @david_picard @CNRS Lol, not for foreigners phds, we need a couple of months at least
0
0
2
RT @arankomatsuzaki: Meta presents Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation achieves performance compar…
0
32
0
RT @Ahmad_Al_Dahle: What a week since we released Llama 3! I couldn’t be more proud of the response. 🏆 Llama 3 70B is now the highest rank…
0
21
0
RT @Ahmad_Al_Dahle: If you want to dive into the details of Imagine Flash, check out the research paper that we published on this today. Re…
0
5
0
RT @AlbertPumarola: Imagine Flash now powers high quality real-time image generation on and @WhatsApp (in the US).…
0
2
0
RT @artsiom_s: Crazy, indeed! For me it was such a fun journey as well: 1. To build a demo in ~1 month 2. To see how it sparkled excitemen…
0
1
0