←
Susung Hong215 posts
Susung Hong avatar

Susung Hong

@SusungHong

PhD student @uwcse | Intern @Google | Generative simulation and video/3D

◷ Joined October 2022▧ 17 Photos and videos
Susung Hong avatar
Susung Hong@SusungHong·Mar 12

🎬Introducing COMIC — fully automated AI comedy Can AI be funny? We've seen AI solve math and code. Comedy is the opposite extreme, whose success is hard to define. 🍿Watch full videos here: susunghong.github.io/COMIC 📄See how we tackle open-ended comedy: arxiv.org/abs/2603.11048

0:07
thijs avatar
⟳ Susung Hong retweeted
thijs@cdngdev·Nov 16

i recreated THE ENTIRE WORLD in minecraft at 1:1 scale. every building on earth, including your house! to do this, i trained a SOTA world-to-minecraft generator on maps data, complete with furnished home interiors! play and check out your neighborhood: worldcraft.gg

0:36
Jon Barron avatar
⟳ Susung Hong retweeted
Jon Barron@jon_barron·Oct 23

Hi all, I have a new result I'm excited to share. It turns out that *all existing implementations* of softmax and cross-entropy (that's JAX, PyTorch, textbooks, etc) have a subtle bug --- two bugs, actually. A simple rewrite fixes both, and eliminates "slingshots" when grokking:

0:07
Dream Labs avatar
⟳ Susung Hong retweeted
Dream Labs@dreamlabs_ai·Oct 19

Today, Dream Labs is coming out of stealth with Dream-1, a robot foundation model that controls bimanual robots it has never seen, on tasks it was never shown, in places it has never been, from $3/hour. Dream API is live for everyone, today. 🧵

1:59
fofr avatar
⟳ Susung Hong retweeted
fofr@fofrAI·Oct 13

Argon has this amazing natural understanding of the world. It can do so many things from first principles. Here's a pelican riding a bike, using fourier epicycles. Video made by Argon. Time-synced Lyria 3.5 music prompted by Argon.

1:00
fofr@fofrAIOct 13

Gemini 4 Argon is live. blog.google/innovation-and-a… There's a lot to show you.

0:51
Gordon (Guocheng) Qian avatar
⟳ Susung Hong retweeted
Gordon (Guocheng) Qian@guocheng_qian·Oct 12

Introducing Code Video Model 🎬 Amazing work led by @raywzy1 and the team! Agentic coding as the engine for controllable video generation. Scene layout, motion, timing, camera trajectories, and physical dynamics, all in editable code. A coding agent turns prompts into executable programs that render proxy videos. Our training-free early-step conditioning lets a pretrained video model follow the proxy’s structure while adopting a reference image’s appearance. From physics-grounded motion and bullet time to 3D/4D reconstruction and robotics simulation, it all starts with code. Watch the demo and explore more visual results 👇 Project page: code-video-model.github.io/ Paper: code-video-model.github.io/t… Code: github.com/code-video-model/… Data: huggingface.co/datasets/code… Youtube: youtube.com/watch?v=dTtiVkSR…

2:18
Logan Kilpatrick avatar
⟳ Susung Hong retweeted
Logan Kilpatrick@OfficialLoganK·Sep 30

Introducing Gemini 4 Argon, our new frontier model, rolling out to cyber defenders starting today, and more widely as soon as possible. I am really excited by the progress we have made here. Argon is priced at $2 in and $10 out during introductory pricing!

Post attachmentPost attachmentPost attachmentPost attachment
Chase Lean avatar
⟳ Susung Hong retweeted
Chase Lean@chaseleantj·Sep 23

I asked Opus 4.6 to 5.5 to generate a realistic 3d model of a medieval castle. It's scary how much it has improved in the past 7 months.

0:15
Rujun Han avatar
⟳ Susung Hong retweeted
Rujun Han@HanRujun·Sep 22

Recursive Self-Improvement (RSI) is transforming how AI agents evolve, but have we considered that it needs regularization too? 🚀 Excited to share our latest work: RRSI (Regularized Recursive Self-Improvement of Agent Harnesses) arxiv.org/abs/2609.24972!

Post attachment
Kevin Patrick Murphy avatar
⟳ Susung Hong retweeted
Kevin Patrick Murphy@sirbayes·Aug 12

Predicting the answer to interventional "what if?" questions — the outcome of an action you never took — need a *mechanistic* model, not a curve fit. And you can only learn one by *experimenting*. Experiments are costly, so the real game is **data efficiency**. Meet the Model Discovery Agent (MDA). 🧵

Post attachment
Discovery Loop avatar
⟳ Susung Hong retweeted
Discovery Loop@DiscoLoopAI·Aug 5

Introducing Discovery Loop ♾. We’re building AI to run experiments at unprecedented scale and to solve the biggest bottlenecks in science and engineering. Our founders @JeffDean, @Sanjay_Ghemawat, @quocleix, @OriolVinyalsML helped build the AI infrastructure and models that scaled the modern world. Now, we are scaling discovery itself. The future can't wait. Learn more at: discoveryloop.com

Post attachment
Donghoon Ahn avatar
⟳ Susung Hong retweeted
Donghoon Ahn@donghoon_ahn·Jul 7

Attending #ICML2026 this week 🇰🇷 and presenting our paper on diffusion guidance! Training-free, no extra NFE, essentially a free-lunch sampling method to reduce hallucinations in diffusion models. hyeon-cho.github.io/TAG/ Also happy to chat about diffusion models, DM me!

Post attachment
Google AI avatar
⟳ Susung Hong retweeted
Google AI@GoogleAI·May 28

We wanted to see if we could take simple, physical materials (like cardboard and markers) and use AI to bring them to life. What was the result? A short film starring a bunch of TPUs getting ready for the big stage at Google I/O 2026! Working with director Laurie Rowan and Nexus Studios, we kept human artistry at the center of the film by blending puppetry and 3D animation with our models to do the following ↓ Nano Banana: Generated beautifully stylized first frames from the raw puppet footage and basic 3D animations. @GoogleAIStudio: Built a custom tool inside the platform to test these frames at scale, ensuring pixel-perfect consistency Gemini Omni & experimental @GoogleDeepMind Models: Merged the base animation and stylized frames to elevate the final piece to a cinematic level. Our AI pipelines were specifically designed to protect the crafty details that give these films their heart, like the tiny human imperfections of puppetry, or the nuance an animator can build into an expression.

2:58
Przemek Chojecki | PC avatar
⟳ Susung Hong retweeted
Przemek Chojecki | PC@prz_chojecki·May 24

Another 9 open Erdos problems solved, this time by DeepMind team. Interesting loop of LLM - Lean agents working autonomously, and only after it's verified formally, going through human review.

Post attachment
OpenAI avatar
⟳ Susung Hong retweeted
OpenAI@OpenAI·May 20

Today, we share a breakthrough on the planar unit distance problem, a famous open question first posed by Paul Erdős in 1946. For nearly 80 years, mathematicians believed the best possible solutions looked roughly like square grids. An OpenAI model has now disproved that belief, discovering an entirely new family of constructions that performs better. This marks the first time AI has autonomously solved a prominent open problem central to a field of mathematics.

2:38