Ayush Saraf

ML Engineer @ Meta Reality Labs

[Nikhil Keetha @Nik__V__]

Eventful @CVPR 2026 coming up! Presenting some of our latest research on scaling 3D, 4D & World Models 🚨

My talk at the Image Matching 2026 Workshop June 4th Room 504 1:45 pm LT -
Scaling Representation Learning for Correspondence to Spatial Intelligence! Join for🌶️ takes

@PeterHedman3 @RamananDeva talks at the ScanNet++ Workshop on View Synthesis & 3D Worlds - June 3rd R 710 3:40 pm LT

Peter Kontschieder presenting World Modeling research (including stuff from @ethanjohnweber & team) - June 4th R 607 8 am LT, June 4th R 203 2:30 pm LT

@JayKarhade @CMU_Robotics presenting Any4D - June 6th Poster Session 3 ExHall F 11:45 am LT, 4D Vision & 4D World Models Workshop Orals: June 4th R 506 4:30 pm LT, June 4th R 203 5 pm LT

Lastly @OmarAlama @AviBh11 presenting our @AirLabCMU semantic scene understanding research - Findings (June 7th 7:30 am LT ExHall A) & OpenSUN3D Workshop (June 3rd afternoon)

Sadly my first in person CV conference will have to wait 🥲but.. do attend for a sneak peek on what we are cooking! 👀🧵👇

[el.cine @EHuanglu]

AI storytelling is crazy now

chatgpt image 2 can turn any story idea into storyboard with cast design.. then feed it to seedance 2 to get a full film scene.. this workflow is crazy on arcads

step by step tutorial with prompts:

[Jaya Gupta @JayaGup10]

https://t.co/5vDrndcmFn

[Ayush Saraf @ayush29feb]

I have been using claude to do AI research. Yesterday I pulled out a pen and paper again because…

[kache @yacineMTB]

you can outsource your thinking
but you cannot outsource your understanding

[kache @yacineMTB]

you can outsource your thinking
but you cannot outsource your understanding

[Andrej Karpathy @karpathy]

This is the the quote I've been citing a lot recently.

[Ning Yu @realNingYu]

📢 Eyeline Labs and Netflix’s latest research, 🎥Vista4D🎥, accepted at #CVPR2026 as a 🌟Highlight🌟 paper, advances virtual cinematography and scene control with video generation.
🎥 Vista4D synthesizes the dynamic scene represented by an input video from novel camera trajectories and viewpoints by grounding video generation in a 4D point cloud. Our method maintains geometric and physical plausibility under imprecise 4D reconstruction of real-world videos.
🎥 Vista4D unlocks video reshooting beyond camera control. By directly editing the 4D point cloud, our method preserves scene information from casual captures and enables 4D scene editing and recomposition.

This work is part of the ongoing research and development at @eyelinestudios and @netflix, and we look forward to seeing its techniques and workflows adopted in future productions.
✊ Kudos to the team: @kuanhenglin, Zhizheng Liu, @pablosalamancal, @yash2kant, @RyanBurgert, @Yuancheng_Xu0, @Koichi_N_, Yiwei Zhao, @zhoubolei, @micahgoldblum, @debfx, @realNingYu

📰 Paper: https://t.co/PsuWi1xQqs
🌐 Project: https://t.co/SoUJW1krO1
⌨️ Code: https://t.co/vcbfeqIJ3o

[Etai Sella @etai_sella]

Do you like image editing? Don't like prompt engineering? Want to see what a giraffe-duck hybrid looks like?
If you answered yes at least once, you may like our new #SIGGRAPH2026 paper: LooseRoPE, which presents a new, prompt-free way to edit images using simple visual cues 👇

[World Labs @theworldlabs]

2 Weeks. New Tools. Infinite Worlds🚀

The World Jam is LIVE. Build the future of interactive 3D with Marble 1.1 + Spark LoD.

Join our Discord to start building.
More info below 👇

[Yakov @yak32]

I finally finished my Gaussian Splat based FPS demo.

It's a @playcanvas project, runs in a browser. On a real photoscan. With physics, baked lighting, pathfinding NPCs.

Here's how 👇

[Albert Omoss @albertomoss]

A few months ago I started writing a Photoshop alternative built on a node graph. Mac and Windows, native C++, 74 nodes. Every operation is non-destructive. Paint, masks, warps, the whole toolset. Nothing bakes.

Launching Tuesday Apr 28. Want to beta test this week? Reply BETA.

[Ayush Saraf @ayush29feb]

Couldn’t agree more

[Santiago @svpino]

Most people write worse code than AI does.

I've worked in absolutely horrible codebases, 100% written and messed up by humans.

So why do we complain about AI-generated slop code today?

Because of the scale at which we are producing it.

Before, you needed a bad programmer to manually write and deploy a ton of bad code.

Today, you can generate virtually unlimited bad code very cheaply and without any constraints.

So the quality of the code might be improving, but the overall amount of technical debt is increasing exponentially.

[Santiago @svpino]

Most people write worse code than AI does.

I've worked in absolutely horrible codebases, 100% written and messed up by humans.

So why do we complain about AI-generated slop code today?

Because of the scale at which we are producing it.

Before, you needed a bad programmer to manually write and deploy a ton of bad code.

Today, you can generate virtually unlimited bad code very cheaply and without any constraints.

So the quality of the code might be improving, but the overall amount of technical debt is increasing exponentially.

[John Doomer @jonathandoomer]

@OpenAI "Chat are you sure I'm on the right road?"

"Absolutely just keep going straight"

[Bilawal Sidhu @bilawalsidhu]

Pokémon Go players captured 30 billion images and built one of the most detailed 3D maps in the world. Niantic just licensed it to train delivery robots. I actually sat down with their CTO, co-creator of Google Earth: https://t.co/Hm2EYCbvIE

What he described makes the picture a lot clearer. But it also opens a much bigger question -- because Niantic is far from the only company mapping reality right now, and the others are capturing way more than parks and statues.

[Andrew Curran @AndrewCurran_]

OpenAI plans to have an 'autonomous Al research intern' up and running by September of this year. And by 2028, a fully automated multi-agent research team.

[Peter Holderrieth @peholderrieth]

We are also releasing self-contained lecture notes that explain flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI.

📖 Read the notes here: https://t.co/RULWDgn9pm

Joint work with @EErives40101.

[Oliver Prompts @oliviscusAI]

🚨 BREAKING: Someone just open-sourced a tool that turns the real world into a playable Minecraft map.

It pulls data directly from OpenStreetMap and generates your exact neighborhood, city, or street block by block.

100% Open Source.

[World Labs @theworldlabs]

🥇 1st place: Musée du Monde
An interactive museum where visitors step inside famous paintings. From Van Gogh’s bedroom to worlds inspired by Vermeer and Matisse, each artwork becomes a fully explorable 3D environment generated with Marble.

[Lex @lexx_aura]

Animated AI short film 🤯 this is truly a masterpiece

Midjourney + Nano Banana Pro + Seedance 2.0