Junyoung Chung (@junyoungch) / X

Junyoung Chung

121 posts

Junyoung Chung

@junyoungch

Research Scientist at @GoogleDeepMind GenAI: Gemini Omni, AlphaStar, AlphaCode, Veo Past: @Mila_Quebec

London, UK

scholar.google.co.uk/citations?user…

Joined September 2016

Pinned
Junyoung Chung
@junyoungch
May 19
We just announced Gemini Omni Flash today! Excited to see what our users generate with it.
Google DeepMind
@GoogleDeepMind
May 19
We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵
00:00
339
Junyoung Chung
@junyoungch
Sep 20, 2024
After seven wonderful years, I’ve left @GoogleDeepMind. I was incredibly fortunate to work alongside some of the brightest minds in our field. I’m excited to join @Microsoft AI as a member of the technical staff. I’ll be focusing on building LLMs. It’s time to 🚢
72K
Junyoung Chung
@junyoungch
Feb 2, 2022
#AlphaCode happy to share what I have been working on finally! It's amazing to see what we can achieve with deep learning. Looking forward to see what comes next!
Google DeepMind
@GoogleDeepMind
Feb 2, 2022
Introducing #AlphaCode: a system that can compete at average human level in competitive coding competitions like @codeforces. An exciting leap in AI problem-solving capabilities, combining many advances in machine learning! Read more: dpmd.ai/Alpha-Code 1/
Junyoung Chung
@junyoungch
Dec 14, 2021
Recent work with my colleagues at DeepMind! We show in our paper that unrolling the denoising process of autoencoders during training can lead to a good performance in machine translation and language modelling.
Google DeepMind
@GoogleDeepMind
Dec 14, 2021
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/
GIF
Junyoung Chung
@junyoungch
May 14, 2024
Happy to have played a part in building Veo, our new video model family!
Google DeepMind
@GoogleDeepMind
May 14, 2024
Introducing Veo: our most capable generative video model. 🎥 It can create high-quality, 1080p clips that can go beyond 60 seconds. From photorealism to surrealism and animation, it can tackle a range of cinematic styles. 🧵 #GoogleIO
00:00
2.9K
Junyoung Chung
@junyoungch
Sep 19, 2024
It's great to see that what I worked on at Google DeepMind is landing on YouTube shorts
Google DeepMind
@GoogleDeepMind
Sep 18, 2024
Our most advanced generative video model Veo is coming to @YouTube Shorts to help creators bring their ideas to life. 🪄 dpmd.ai/veo-YT-shorts
00:00
10K
Junyoung Chung
@junyoungch
Feb 2, 2022
Replying to @DBahdanau
I fully agree with you Dima, there is a long way to go. :)
Junyoung Chung
@junyoungch
Dec 9, 2022
Very proud to see our work featured in @ScienceMagazine as the front cover!
Science Magazine
@ScienceMagazine
Dec 8, 2022
#AlphaCode—a new #AI system for developing computer code developed by @DeepMind—can achieve average human-level performance in solving programming contests. Learn more this week in Science: scim.ag/Nn
Junyoung Chung
@junyoungch
Jun 17, 2024
Finally, Veo can make 🔊 from 🎞️
Google DeepMind
@GoogleDeepMind
Jun 17, 2024
We're sharing progress on our video-to-audio (V2A) generative technology. 🎥 It can add sound to silent clips that match the acoustics of the scene, accompany on-screen action, and more. Here are 4 examples - turn your sound on. 🧵🔊 dpmd.ai/v2a
00:00
3.6K
Junyoung Chung
@junyoungch
Oct 4, 2024
Exactly 😂
roon
@tszzl
Oct 4, 2024
this is how the largest training runs in the world are done
GIF
1.6K
Junyoung Chung
@junyoungch
May 29, 2024
Veo can generate 🎞️ from 🖼️ 👀
Google DeepMind
@GoogleDeepMind
May 29, 2024
Our video generation model Veo can create clips from a single reference image. 🖼️ These can follow the original visual style alongside instructions from a text prompt. Let’s take a look. 🧵
00:00
349
Junyoung Chung
@junyoungch
Oct 4, 2024
Cool stuff from @AIatMeta
AI at Meta
@AIatMeta
Oct 4, 2024
🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in
00:00
775
Junyoung Chung
@junyoungch
May 15, 2024
This version with sound is cool!
Ammaar Reshi
@ammaar
May 15, 2024
Time for a fully AI generated music video! Using @GoogleDeepMind’s impressive Veo video from I/O + ElevenLabs Music and SFX models. 🔥
ElevenLabs
00:00
ElevenLabs
2K
Junyoung Chung
@junyoungch
Dec 9, 2022
Replying to @junyoungch
Here is a nice animation version of the cover.
Google DeepMind
@GoogleDeepMind
Dec 8, 2022
In @ScienceMagazine, we present #AlphaCode - the first AI system to write computer programs at a human level in competitions. It placed in the top 54% of participants in coding contests by solving new and complex problems. How does it work? 🧵 dpmd.ai/alphacode-scie…
00:00