
Research Scientist at @GoogleDeepMind | Scaling RL for Gemini Past Work: AlphaStar, AlphaCode, Veo, Gemini Omni Past: @Mila_Quebec
London, UK
Joined September 2016
- Tweets125
- Following161
- Followers1.6K
- Likes634
Junyoung Chung retweeted
Introducing Gemini 4 Neon!
Our team pushed hard to bring frontier-level intelligence to a faster, more cost-efficient model for complex, daily work.
We have really enjoyed using this model internally. Excited for you all to try it!
Junyoung Chung retweeted
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!
Junyoung Chung retweeted
Just two weeks after rolling out Gemini 4 Argon, excited to share a preview of Gemini 4 Carbon - our next frontier model. It has state-of-the-art long horizon coding capabilities driving SOTA performance across the cybersecurity defense lifecycle including detection, validation, and remediation. It also ranks #1 overall on the recently updated v5.0 of Artificial Analysis Intelligence Index at 59.
We're starting by rolling out to a subset of cyber defenders through our Fairwind Program this week and soon expanding access further. Read more at: blog.google/innovation-and-a…
Junyoung Chung retweeted
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.
> 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.
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 ↓ teapawt.org/i/status/2056786446636…
Junyoung Chung retweeted
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:
Junyoung Chung retweeted
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!
Junyoung Chung retweeted
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:)
Junyoung Chung retweeted
amen
those with savior and superiority complex, obsessed with sci fi, blinded by dollar signs, devoid of empathy, and severely gullible.
I wrote about the tragic death of Adam Raine and the venal negligence of "AI Safety." argmin.net/p/the-banal-evil-…
Junyoung Chung retweeted
After Veo 3, Genie 3, Imagen 4, ... we present nano-banana*! 🍌🚀
(*aka Gemini-2.5-Flash-Image-Preview)
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 🧵
Junyoung Chung retweeted
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.
Junyoung Chung retweeted
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.
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!
Junyoung Chung retweeted
Veo 2 and the new Imagen 3 update just dropped. Amazing effort by the team!!
Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥
We’re also releasing an improved version of our text-to-image model, Imagen 3 - available to use in ImageFX through @LabsDotGoogle. → goo.gle/veo-2-imagen-3
Junyoung Chung retweeted
Sora is here for Plus and Pro users at no additional cost! Pushing the boundaries of visual generation will require breakthroughs both in ML and HCI. Really proud to have worked on this brand new product with @billpeeb @rohanjamin @cmikeh2 and the rest of the Sora team!
sora.com
























