Adithya Iyer

WM @ @amilabs . Ex @morphic / NYU. IIT Bombay'21, Ex boring Consultant turned Ghibli Art maker

[Saining Xie @sainingxie]

check out RAEv2 led by Jas. through extensive exps, we found some really intriguing behaviors showing why strong representation encoders are key for pixel decoders.
spoiler: it’s not about hillclimbing fid; new metrics like ep@fid-k/fdr^k show there’s a lot more left to explore!

[Adithya Iyer @adithy2]

To a large extent - yes, we wanted the model to use as much context from the original video for consistency of subjects/movement. Logically, it's easy to train one which can fix issues in the original video too, but for the purposes of this work: subject consistency with source > aesthetics , in terms of importance.

[Adithya Iyer @adithy2]

Introducing Reshoot-Anything 🎦, our method to change perspective on video, while being trained largely on *in-the-wild* videos 🧵1/8

[Adithya Iyer @adithy2]

@hckinz Hi! Vista4D was concurrent work to ours, and takes some different arch decisions, which are quite interesting in itself. Our method builds on Wan2.2, and more so tackles this pressing issue : can you scale a vid2vid by using raw footage, using very scarce synthetic data

[Adithya Iyer @adithy2]

Weights, code and links:
Paper : https://t.co/VWXm4wqal4
Website : https://t.co/DafYUSNBg0
Github : https://t.co/gdxwgptwA8

8/8

[Adithya Iyer @adithy2]

Work done with my awesome collaborators:
@avinash_plwl ,Shivin Yadav, @not_ali_afridi, @HarikumarMidhun. Special shoutout to
@jdkanani and @morphic for the support, compute and inspiration! 7/8

[Saining Xie @sainingxie]

vision🍌 is here https://t.co/Ued6GGk4Et
if you got into computer vision the way I did, starting with pixel-level labeling tasks like segmentation, edges, depth, or surface normals, you’ll probably feel the same seeing these results -- something big has quietly shifted, and it’s going to change how we approach these problems for good 🧵

[Adithya Iyer @adithy2]

@TongPetersb @sainingxie @ylecun @mengyer @YiMaTweets @LukeZettlemoyer @liuzhuang1234 Congrats peter!

[Adithya Iyer @adithy2]

@sanghyunwoo1219 @amilabs congrats @sanghyunwoo1219 !

[Saining Xie @sainingxie]

i’m joining forces with @ylecun and an incredible group of people to start AMI Labs @amilabs.
AMI isn’t a conventional lab. we don’t intend to become one.
a lot to say about why this moment matters, but for now we’re heads down building.

join us: https://t.co/zXj1IyBYDc

[Amandeep Kumar @Amandeep__kumar]

🚀 Unlocking Standard Diffusion Transformers on Representation Encoders

Why do standard DiTs fail to converge on high-dimensional features like DINOv2? 📉 We found the answer isn't just "more parameters"—it's Geometry.

Introducing Riemannian Flow Matching with Jacobi Regularization (RJF)

📄 Paper: https://t.co/yMutIh2mh5

[Adithya Iyer @adithy2]

Neat! Been waiting for something like this

[Brian Li @Brian_Bo_Li]

https://t.co/vArmj0QkET

[Palak Zatakia @palakzat]

Hiring a Content & Narrative Operator to work with me at @morphic.

- Someone young, obsessed with AI and startups
- Uses ChatGPT / Claude for writing tasks DAILY

You could be working remotely, but it’s very crucial that you live on Twitter. 😺

Just DM me. Or send this tweet to someone you know.

[Dorksense @Dork_sense]

Inside @morphic you can extract frames directly from any grid images generations

Saves the mundane task of manual cropping

this is how it should be!

[Morphic @morphic]

What if Odyssey was reimagined as an anime?

Inspired by the timeless epic, this is our anime interpretation of Odysseus’ journey.

Same myth. New visual language. Made entirely with @morphic.