
AI Scientist @Roblox | Video world models
Joined March 2013
- Tweets134
- Following701
- Followers690
- Likes1.3K
Pinned Tweet
Excited to share Morpheus AI is coming out of stealth and joining Roblox!
Grateful to have joined Xun as a founding member and helped build video world models over the past several months, alongside some of the most talented people I've worked with.
Thanks to the entire team. Excited to keep building world models at Roblox, now at a scale that reaches millions of players.
I'm excited to announce that the Morpheus AI team is joining Roblox!
Over the past two years, I’ve focused on developing the foundational architectures behind modern video world models, including Self Forcing and AR-DiT. This work unlocked something unprecedented: the ability to move beyond offline, pre-rendered AI video generation and instead simulate interactive worlds in real time. Realizing the massive potential of this technology is what drove me to found Morpheus in August 2025. In the months since, our incredible team has pushed those boundaries further than we ever thought possible.
We've always believed video world models will reshape how games are created. Roblox Reality is an ambitious bet on that exact future, and it lines up perfectly with what we set out to do: bridging the gap between deterministic game engines and generative world models. Joining Roblox means our technology will help power experiences that reach millions of players every day.
To our team, to @a16z and other investors, and to the advisors, partners, and supporters who believed in this from the very beginning — thank you.
We're just getting started. Excited to build this at scale.
Chris Rockwell retweeted
Welcome to Roblox
Morpheus AI is joining Roblox. This acquisition will dramatically cut the time and cost of building high-fidelity, interactive worlds and unlock new possibilities for creators everywhere.
about.roblox.com/newsroom/20…
Chris Rockwell retweeted
Hello! If you are interested in dynamic 3D or 4D, don't miss the oral session 3A at 9 am on Saturday:
@zhengqi_li
will be presenting "MegaSaM"
I'll be presenting "Stereo4D"
and
@QianqianWang5
will be presenting "CUT3R"
Chris Rockwell retweeted
Excited to share our CVPR 2025 paper on cross-modal space-time correspondence!
We present a method to match pixels across different modalities (RGB-Depth, RGB-Thermal, Photo-Sketch, and cross-style images) — trained entirely using unpaired data and self-supervision.
Our approach learns correspondences through contrastive random walks across visual modalities.
#CVPR2025 (1/6)
Chris Rockwell retweeted
Ever wondered how a scene sounds👂 when you interact👋 with it?
Introducing our #CVPR2025 work "Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes" -- we make 3D scene reconstructions audibly interactive!
yimingdou.com/hearing_hands/
Chris Rockwell retweeted
Can AI image detectors keep up with new fakes?
Mostly, no. Existing detectors are trained using a handful of models. But there are thousands in the wild!
Our work, Community Forensics, uses 4800+ generators to train detectors that generalize to new fakes.
#CVPR2025 🧵 (1/5)
Chris Rockwell retweeted
Hello! If you like pretty images and videos and want a rec for CVPR oral session, you should def go to Image/Video Gen, Friday at 9am:
I'll be presenting "Motion Prompting" @RyanBurgert will be presenting "Go with the Flow" and @ChangPasca1650 will be presenting "LookingGlass"
Excited to share ☀️Lightspeed⚡, a photorealistic, synthetic dataset with ground truth pose used for benchmarking alongside DynPose-100K!
Now available for download: huggingface.co/datasets/nvid…
Paper accepted to #CVPR2025: arxiv.org/abs/2504.17788
Ever wish YouTube had 3D labels?
🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose!
Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯
Download: huggingface.co/datasets/nvid…
Chris Rockwell retweeted
Cameras are key to modeling our dynamic 3D visual world. Can we unlock the 𝘥𝘺𝘯𝘢𝘮𝘪𝘤 3𝘋 𝘐𝘯𝘵𝘦𝘳𝘯𝘦𝘵?! 🌎
📸 𝗗𝘆𝗻𝗣𝗼𝘀𝗲-𝟭𝟬𝟬𝗞 is our answer! @_crockwell has curated Internet-scale videos with camera pose annotations for you 🤩
Download: huggingface.co/datasets/nvid…
Ever wish YouTube had 3D labels?
🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose!
Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯
Download: huggingface.co/datasets/nvid…
Ever wish YouTube had 3D labels?
🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose!
Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯
Download: huggingface.co/datasets/nvid…
🚀DynPose-100K improves learned pose estimation!
DUSt3R finetuned on a small sample of DynPose-100K is competitive with or better than MonST3R, which is trained on a much larger synthetic dataset
More results + webpage: research.nvidia.com/labs/dir…
abs: arxiv.org/abs/2504.17788
Thanks to my great collaborators @jt_tung, @TsungYiLinCV, @liu_mingyu, David Fouhey and @chenhsuanlin
Chris Rockwell retweeted
Video generation models exploded onto the scene in 2024, sparked by the release of Sora from OpenAI. I wrote a blog post on key techniques that are used in building large video generation models:
yenchenlin.me/blog/2025/01/0…
Chris Rockwell retweeted
Introducing 👀Stereo4D👀
A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories.
We used Stereo4D to make a dataset of over 100k real-world 4D scenes.
Chris Rockwell retweeted
What happens when you train a video generation model to be conditioned on motion?
Turns out you can perform "motion prompting," just like you might prompt an LLM! Doing so enables many different capabilities. Here’s a few examples – check out this thread 🧵 for more results!
Chris Rockwell retweeted
We present Global Matching Random Walks, a simple self-supervised approach to the Tracking Any Point (TAP) problem, accepted to #ECCV2024. We train a global matching transformer to find cycle consistent tracks through video via contrastive random walks (CRW).
Chris Rockwell retweeted
📢 Introducing our #ECCV2024 work, COCO-ReM (COCO Refined Masks), for more reliable benchmarking of object detectors, crucial for the future of object detection research.
Paper: arxiv.org/abs/2403.18819
Code: arxiv.org/abs/2403.18819
Website: cocorem.xyz/
Chris Rockwell retweeted
📢Presenting 𝐃𝐄𝐏𝐈𝐂𝐓: Diffusion-Enabled Permutation Importance for Image Classification Tasks #ECCV2024
We use permutation importance to compute dataset-level explanations for image classifiers using diffusion models (without access to model parameters or training data!)
Excited to present our #CVPR2024 *Highlight* FAR on Friday at 10:30 a.m, Arch 4A-E Poster #31. Please feel free to stop by!
FAR significantly improves correspondence-based methods using end-to-end pose prediction, making it applicable to many SOTA approaches!
📢 Presenting 𝐅𝐀𝐑: 𝐅𝐥𝐞𝐱𝐢𝐛𝐥𝐞, 𝐀𝐜𝐜𝐮𝐫𝐚𝐭𝐞 𝐚𝐧𝐝 𝐑𝐨𝐛𝐮𝐬𝐭 𝟔𝐃𝐨𝐅 𝐑𝐞𝐥𝐚𝐭𝐢𝐯𝐞 𝐂𝐚𝐦𝐞𝐫𝐚 𝐏𝐨𝐬𝐞 𝐄𝐬𝐭𝐢𝐦𝐚𝐭𝐢𝐨𝐧 #CVPR2024
FAR builds upon complimentary Solver and Learning-Based works yielding accurate *and* robust pose!
crockwell.github.io/far/
















