FAIR (@AIatMeta) | Ph.D. | Generative World Models
Joined March 2021
- Tweets332
- Following301
- Followers410
- Likes682
moab.arar retweeted
I’ve spent the last decade working to make AI as powerful for 3D as it is for text and images - from industry, through my PhD, to leading my own research lab as a professor.
I started Thrixel to put that research directly into people's hands: a 3D creation platform for the agentic era that lets anyone build complete, interactive 3D worlds using AI.
It’s especially exciting to build Thrixel alongside people I’ve researched with for years. Together, we’re bringing fundamental research breakthroughs straight into our core engine.
Here’s a peek behind the scenes at Thrixel ↓
Thrixel is building the 3D creation engine that powers the agentic world. Born out of years of core 3D AI research, Thrixel aims to lower the barrier to entry to building in 3D and democratize the 3D creation process. Thrixel creates assets with named, editable parts, that human creators and AI agents can directly control across games, simulations, and a wide range of other applications.
See what we’re building: thrixel.com
math_v1_v2_final_final.md
We've updated our GitHub math repo with 6 new Lean formalizations, 19 modifications, and 3 withdrawals. The repo now has ~42% top-line results formalized. We will continue to update the repo with new formalizations and with any errata we notice.
github.com/openai/math/blob/…
moab.arar retweeted
Happy to share our recent work: Solaris, our take on the future of generative UIs
Today, we're sharing new research on Solaris, our first Interface World Model.
Solaris is a new kind of operating system that generates interactive interfaces frame by frame, in real time, with no code. We find that Solaris outperforms frontier LLMs when generating new interfaces, across structural similarity and information retention. Read more and request early access at the link below.
moab.arar retweeted
1/ New paper: Parallel Decoding Distillation (PDD)!🚀
To accelerate diffusion/flow models, trajectory distillation usually merges consecutive ODE steps into 1 larger step. PDD changes this by predicting MULTIPLE ODE steps in 1 network eval.🧵
w/ @julberner @ArashVahdat Chao Liu
moab.arar retweeted
Excited to share that Inspiration Seeds has received an Honorable Mention award this year at SIGGRAPH! 🎉
👉kfirgoldberg.github.io/Inspi…
Huge thanks and congrats to the best team! @kfir99 @EladRichardson
Looking forward to seeing you in LA in July!🌱
Creative work often starts before we can describe what we're looking for. What role can generative models play at this stage?
🌱Our new work, Inspiration Seeds, reveals hidden visual connections between images, creating a purely visual exploration space.
🔗kfirgoldberg.github.io/Inspi…
moab.arar retweeted
Even today, with powerful image editing models, making fine-grained structural changes to 3D shapes remains a major challenge.
In our new #SIGGRAPH2026 paper, Prox-E, we use primitive-based abstraction to leverage VLMs for precise, reasoning-based 3D editing!
👇
moab.arar retweeted
Excited to share our work accepted to #SIGGRAPH2026 ! Video generation models struggle with something few talk about: their transformations don't evolve smoothly. You get long boring stretches... then a sudden semantic jump where everything "catches up" at once.
moab.arar retweeted
1/7
When rewards conflict, what should RL post-training of diffusion models optimize?
In visual generation, objectives are often in tension:
Prompt adherence can conflict with source preservation.
Photorealism can conflict with stylization.
In our new paper, ParetoSlider, we introduce a multi-objective RL framework that trains a single diffusion model for continuous control over competing reward objectives 🧵
moab.arar retweeted
The FAIR Montréal office is expanding!
We're looking for folks to join us who are exciting about world modelling. Hiring for both recent grads as well as more experienced researchers.
Feel free to reach out, but please read the posting first :)
metacareers.com/profile/job_…
moab.arar retweeted
3D editing has long relied on workarounds: per-asset optimization, 2D view propagation, or hacking frozen priors. The bitter lesson is the same one image editing already learned. Train a native model, end-to-end.
Introducing ShapeUP, accepted to SIGGRAPH 2026 💫
moab.arar retweeted
Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
paper: huggingface.co/papers/2603.2…
moab.arar retweeted
I am *very* excited to announce our SIGGRAPH 2026 workshop:
Lines & Minds: Visual Abstraction in Art, Psychology, and Computer Graphics 🎨🧠🫖
🔗 lines-and-minds.github.io
📅 Sunday, July 19
Join us to explore how visual abstraction shapes how we think, create, and communicate.
moab.arar retweeted
Video models as Physics simulators. 🌍🎥
[1/] In our latest work, WinDiNet, we finetuned a pre-trained video model into a differentiable physics engine. 1000x faster than traditional CFD solvers.
Project page: rbischof.github.io/windinet_…
Abs: arxiv.org/abs/2603.21210
moab.arar retweeted
surprising repurposing of video diffusion models
🌬️🏢
Video models as Physics simulators. 🌍🎥
[1/] In our latest work, WinDiNet, we finetuned a pre-trained video model into a differentiable physics engine. 1000x faster than traditional CFD solvers.
Project page: rbischof.github.io/windinet_…
Abs: arxiv.org/abs/2603.21210
Video models as Physics simulators. 🌍🎥
[1/] In our latest work, WinDiNet, we finetuned a pre-trained video model into a differentiable physics engine. 1000x faster than traditional CFD solvers.
Project page: rbischof.github.io/windinet_…
Abs: arxiv.org/abs/2603.21210
[3/] We fine-tuned LTX with 10k 2D urban wind flow simulations by (i) fine-tuning the VAE decoder with physics-informed losses, and (ii) replacing the text encoder with a wind speed and direction embedder.
[4/] Shout out to Janne Perini and Rafael Bischof for their hard work, and the great team: Ayça Duran, Michael A. Kraus, Siddhartha Mishra, and @bernd_bickel.
moab.arar retweeted
Creative work often starts before we can describe what we're looking for. What role can generative models play at this stage?
🌱Our new work, Inspiration Seeds, reveals hidden visual connections between images, creating a purely visual exploration space.
🔗kfirgoldberg.github.io/Inspi…