David Fan

AMI Labs | ex-Meta FAIR | @Princeton CS '19
Building the next revolution of AI models that understand the real world.

[David Fan @DavidJFan]

[1/9] What happens when you treat vision as a first-class citizen during multimodal pretraining? To find out, we studied the design space of training Transfusion-style models that input and output all modalities, from scratch. Here is what we learned about visual representations, data, world modeling, architecture, and scaling behavior!

Paper: https://t.co/ik6JGgjbTD
Website: https://t.co/nklaggMEfT

@TongPetersb, @DavidJFan, @__JohnNguyen__, @ellisbrown, @GaoyueZhou, @JasonQSY, @boyangzheng, @webalorn, @han_junlin, @rob_fergus, @NailaMurray, @gh_marjan, @ml_perception, Nicolas Ballas, @_amirbar, Michael Rabbat, Jakob Verbeek, @LukeZettlemoyer, @koustuvsinha, @ylecun, @sainingxie

[David Fan @DavidJFan]

@raktimgg @amilabs Excited to have you!!

[David Fan @DavidJFan]

@artemZholus Might be because people aren't using the same recipes for high-dim diffusion!

[David Fan @DavidJFan]

@USCIS @StateDept The entire big tech industry is going to crumble after this 😂 good luck staying competitive in STEM

[Jaskirat Singh @1jaskiratsingh]

In Oct last year, Representation Autoencoders provided an elegant solution to unified tokenization for understanding and generation.

Today we make them a bit more simple. a bit more general.
Result: >10x faster convergence, better reconstruction, better generation.
And yes we test them on T2I and world models :)

Introducing RAEv2

[John Nguyen @__JohnNguyen__]

Today we released the code for our CVPR 2026 paper, Flowception.

Flowception bridges fully bidirectional sequence modeling and autoregressive generation by inserting frames via learned order, then denoising them with continuous flow.

Website: https://t.co/BujPaGRJ7h
Code: https://t.co/VJNBFBvIbV

[David Fan @DavidJFan]

@__JohnNguyen__ Congrats John!!

[David Fan @DavidJFan]

@Delong0_0 my low-level vision needs improvement

[David Fan @DavidJFan]

@_sungmin_cha Great work Sungmin!!

[David Fan @DavidJFan]

@TongPetersb @sainingxie @ylecun @mengyer @YiMaTweets @LukeZettlemoyer @liuzhuang1234 So proud of you Peter!! It’s been such an honor to be a part of your journey 😁 still remember the first day we met thru Zhuang at that restaurant haha

[David Fan @DavidJFan]

@gberta227 @yblin98 Congrats Gedas!! Huge milestone 😁 super happy for you

[David Fan @DavidJFan]

@weiyaow1 @thinkymachines Congrats Weiyao!! Sad to see you leave but super excited for you 😁 Hope to see you again soon

[AMI Labs @amilabs]

Heading to ICLR in Rio 🇧🇷?
We’re hosting our first networking mixer on April 24.
Meet AMI’s technical team and cofounders, and learn more about what we’re building.
Food, drinks, and great conversation included.
Register at https://t.co/PQmb6wAoFZ

[David Fan @DavidJFan]

Congrats Dr. @TongPetersb!! Your research journey has clearly culminated in a very cohesive and inspiring narrative that unifies several areas of work with much scope for future expansion :D It's a testament to your work ethic, good taste in problems, and attention to detail. I'm so proud of you! Very lucky to learn from you

[John Nguyen @__JohnNguyen__]

Congrats Dr. Tong!
Really glad to be a part of your PhD journey @TongPetersb

[David Fan @DavidJFan]

@raktimgg Woo hoo!

[David Fan @DavidJFan]

Check out the code and data for DexWM!
Training + Inference Code: https://t.co/F1er5X3BRY
Robocasa Data: https://t.co/XYFxNqSCaU

[Raktim Gautam Goswami @raktimgg]

The code for DexWM is now publicly available: https://t.co/nLCQtWzPa8.
The repository includes the full training and evaluation pipelines, along with custom dexterous manipulation datasets generated in RoboCasa, making it easy to reproduce our results and build on top of this work.

[David Fan @DavidJFan]

@jihanyang13 Same here!!

[David Fan @DavidJFan]

This week I joined AMI Labs as a founding member of the NYC lab! I'm super excited to build AI systems that truly understand the physical world. I'm also excited to help build the research agenda, culture, and team from the ground up, and learn what it takes to build a company. It's a real privilege to be here.

The last ~2 years at FAIR have been the most rewarding of my professional life so far. When I first started doing research almost 10 years ago, joining FAIR felt like a pipe dream. I became a better researcher, open-sourced for the first time (V-JEPA 2, WebSSL, MetaMorph, DexWM), grew as a person, made life-long friends, and even rekindled old hobbies — like playing clarinet with the Meta NYC orchestra.

I want to thank Mike Rabbat, Maryam Fazel-Zarandi, the JEPA team, and all my amazing colleagues + collaborators who made this dream come true. The research world is small, so I know our paths will cross again. Please stay in touch!

[AMI Labs @amilabs]

Advanced Machine Intelligence (AMI) is building a new breed of AI systems that understand the world, have persistent memory, can reason and plan, and are controllable and safe.

We’ve raised a $1.03B (~€890M) round from global investors who believe in our vision of universally intelligent systems centered on world models. This round is co-led by Cathay Innovation, Greycroft, Hiro Capital, HV Capital, and Bezos Expeditions, along with other investors and angels across the world.

We are a growing team of researchers and builders, operating in Paris, New York, Montreal and Singapore from day one.

Read more: https://t.co/kyVAL7EoFx
AMI - Real world. Real intelligence.

[David Fan @DavidJFan]

@giffmana Dang Switzerland has everything!

[David Fan @DavidJFan]

@ylecun @sainingxie Thank you so much Yann!! It’s a pleasure to work with you again and hope to try the bourgignon next time I visit 😁

[David Fan @DavidJFan]

@shushengyang @jihanyang13 Thanks!! Looking forward to working with you soon