@junyoungch

Research Scientist at @GoogleDeepMind | Scaling RL for Gemini Past Work: AlphaStar, AlphaCode, Veo, Gemini Omni Past: @Mila_Quebec

 London, UK
scholar.google.co.uk/citations?user=2HE7cTEAAAAJ&hl=en
Joined September 2016
  • Tweets122
  • Following162
  • Followers1.6K
Let's goooo! Proud to be part of making this happen.
Google DeepMind
@GoogleDeepMindSep 30
Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
1
18
1,214
Junyoung Chung retweeted
László Gaál
@laszlogaal_Jun 5
Google Omni can recognize objects from an image, not sure how exactly does it but this is not simply a video model. Input is an image (for each group of objects), asking Google Omni to analyze what are the objects and create a short video about them (so one image of the cars without information about their make/model). Again: this model has to be treated more like Nano Banana and not like Veo.
2
8
34
3,228
Junyoung Chung retweeted
fofr
@fofrAIJun 4
> Amateur vertical phone video, 9:16 aspect ratio. Continuous, unbroken handheld shot of a fluffy tabby cat sitting on a sunny windowsill, looking out into a leafy garden. The cat's tail twitches slowly, and its ears rotate slightly toward ambient noises. Sunbeams illuminate dust motes in the air. Sound design: Gentle breeze, distant bird chirps, quiet mechanical purring. No dialogue.
9
3
65
3,801
Junyoung Chung retweeted
Alexander Chen
@alexanderchenMay 29
Gemini Omni 🐦 prompt in 🧵
🤖 Made with AI
51
155
43
1,386
227,588
Junyoung Chung retweeted
fofr
@fofrAIMay 27
> Make this an anatomy demo, showing how the bones and muscles move when the hand moves.
35
60
17
809
223,207
Junyoung Chung retweeted
Min Choi
@minchoiMay 23
Ok Gemini Omni is insane. People can't stop getting creative with it. 10 wild examples.
76
126
9
1,392
279,760
Junyoung Chung retweeted
Google
@GoogleMay 22
Nano Banana for video is here 🍌🎥 Gemini Omni is our new AI model that makes creating and editing videos as easy as having a conversation. Here’s how it works ↓ xitter.cf/i/status/2056786446636…

X. It’s what’s happening

From breaking news and entertainment to sports and politics, get the full story with all the live commentary.

x.com
411
239
49
1,596
221,105
Junyoung Chung retweeted
fofr
@fofrAIMay 23
Scrolling my feed like
🤖 Made with AI
14
15
2
271
11,367
🔍🔍🔍
fofr
@fofrAIMay 19
Gemini Omni Flash: > a recording from a capsule on the london eye, a jerky zoom into something in the distance and then refocusing (with a bit of back and forth) (no timestamp or dialog) Note the world knowledge of London’s landscape, and the way the video is gently moving like the capsules do.
4
396
Junyoung Chung retweeted
Demis Hassabis
@demishassabisMay 19
Gemini Omni is a major leap in world understanding & multimodal editing! It can take photos, video & audio and build entirely new scenes. Over time it’ll be able to handle any input & any output - starting w/ video You can even give it your own videos & iterate on your ideas:
378
904
190
9,375
954,103
Junyoung Chung retweeted
Google AI
@GoogleAIMay 19
By now, you've probably heard about Gemini Omni, our new model designed to create anything from any input, starting with video. But... what's the big deal? Let’s break it down 🧵👇
83
257
38
2,482
228,524
We just announced Gemini Omni Flash today! Excited to see what our users generate with it.
Google DeepMind
@GoogleDeepMindMay 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 🧵
1
5
459
You can test it in the Gemini app and Flow🌊labs.google/fx/tools/flow

Google Flow - AI Creative Studio for Video, Images & Custom Tools

Try Google Flow, the ultimate AI for creatives. Transform ideas into reality using Google’s advanced generative models for cinematic video, images, & tools.

flow.google.com
64
Our second Nano Banana in three months 🚢 🚢. Super proud of the team!! Looking forward to seeing what you'll create with it. Any feedback welcome!
Sundar Pichai
@sundarpichai20 Nov 2025
You went 🍌🍌 for Nano Banana. Now, meet Nano Banana Pro.  It’s SOTA for image generation + editing with more advanced world knowledge, text rendering, precision + controls. Built on Gemini 3, it’s really good at complex infographics - much like how engineers see the world:)
1
10
71
11,540
Junyoung Chung retweeted
Sundar Pichai
@sundarpichai20 Nov 2025
You went 🍌🍌 for Nano Banana. Now, meet Nano Banana Pro.  It’s SOTA for image generation + editing with more advanced world knowledge, text rendering, precision + controls. Built on Gemini 3, it’s really good at complex infographics - much like how engineers see the world:)
805
1,916
610
23,232
4,545,309
Junyoung Chung retweeted
Kyunghyun Cho
@kchonyc28 Aug 2025
amen those with savior and superiority complex, obsessed with sci fi, blinded by dollar signs, devoid of empathy, and severely gullible.
Ben Recht@beenwrekt28 Aug 2025
I wrote about the tragic death of Adam Raine and the venal negligence of "AI Safety." argmin.net/p/the-banal-evil-…

The Banal Evil of AI Safety

Chatbot companies are harmful and dishonest. How can we hold them accountable?

argmin.net
4
3
1
41
9,579
After Veo 3, Genie 3, Imagen 4, ... we present nano-banana*! 🍌🚀 (*aka Gemini-2.5-Flash-Image-Preview)
Google DeepMind
@GoogleDeepMind26 Aug 2025
Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵
3
17
214
17,853
🍌
Aäron van den Oord
@avdnoord26 Aug 2025
You know the team has built a good model when ... people go to a website that randomly serves it some of the time 5 million times
2
422
Junyoung Chung retweeted
Pushmeet Kohli
@pushmeet30 Jul 2025
Our Science team @GoogleDeepMind is relentless. Hot on the heels of AlphaEvolve (algorithms) in May, AlphaGenome (biology) in June, and our IMO gold medal model (maths) last week, we're ready for a new launch. Watch this space. The acceleration is real.
58
141
20
2,677
165,589
We updated our Imagen 4 models and Ultra is tied for #1 on the lmarena leaderboard! The models are available in Google AI Studio and the Gemini API - try them out and let us know what you think.
Arena.ai
@arena25 Jul 2025
Exciting Text-to-Image leaderboard update! Two new Imagen 4.0 models from @GoogleDeepMind just dropped: 🥇 Imagen 4.0 Ultra (v2) ties at #1 with @OpenAI’s GPT-Image-1 🥉 Imagen 4.0 (v2) lands strong at #3 Congrats to the Google Imagen team!
15
51
4
308
105,128
Load more