Daniel Winter

@GoogleAI

[Daniel Winter @_daniel_winter_]

We introduce ObjectDrop, our recent @GoogleAI project, aimed at achieving photorealistic object removal and insertion.

Explore our project page: https://t.co/GOj5uAIF3v
Arxiv: https://t.co/0tNxic4mUI

[Eliahu Horwitz @EliahuHorwitz]

Excited to share this has now been accepted at #NeurIPS2025 as a position paper (<6% acceptance)!🎉

We advocate for systematically studying entire model populations via weight-space learning, and argue that this requires charting them in a Model Atlas.
@NeurIPSConf #NeurIPS
🧵👇

[Nataniel Ruiz @natanielruizg]

We are releasing a paper I'm very excited about. We know test-time scaling is a path to greatly improved results, and achieves reasoning in the case of LLMs. We present a new and promising way to amortize it into training using HyperNetworks for image generation models.

[Eliahu Horwitz @EliahuHorwitz]

@karpathy Thanks for the inspiring talk (as always!). I'm the author of the Model Atlas. I'm delighted you liked our work, seeing the figure in your slides felt like an "achievement unlocked"🙌Would really appreciate a link to our work in your slides/tweet https://t.co/rJjBhMmRjf

[Kevin Lu @kevinlu4588]

When we "erase" a concept from a diffusion model, is that knowledge truly gone? 🤔

We investigated, and the answer is often 'no'!

Using simple probing techniques, the knowledge traces of the erased concept can be easily resurfaced 🔍

Here is what we learned 🧵👇

[Asaf Shul @ShulAsaf]

A quick look on what we were working on in the past months 🎉 more exciting things to come 🙌🏻

[AK @_akhaliq]

Google presents LightLab

Controlling Light Sources in Images with Diffusion Models

[Niv Cohen @CohNiv]

In our #ICLR2025 paper, we introduce WIND 🌬️
A method that embeds a distortion watermark directly in the diffusion noise! Our method ensures that the watermark in one image does not reveal information about the watermark in other images 🤫
📝 https://t.co/jmEw4g3scN

(1/5)

[Eliahu Horwitz @EliahuHorwitz]

🚨 New paper alert! 🚨

Millions of neural networks now populate public repositories like Hugging Face 🤗, but most lack documentation. So, we decided to build an Atlas 🗺️

Project: https://t.co/1JpsC6dCeg
Demo: https://t.co/4Xy7yLdIZY

🧵👇🏻 Here's what we found:

[Nataniel Ruiz @natanielruizg]

Crazy work by colleagues in my team!

[Asaf Shul @ShulAsaf]

🚨
Excited to share ObjectMate our latest from @GoogleAI for zero-shot subject-driven generation & insertion
🚨

🔗 project page: https://t.co/uBeJgccH3W

📄Arxiv: https://t.co/J2Ya8TLLeP

[Daniel Winter @_daniel_winter_]

Many thanks to my great collaborators @ShulAsaf Matan Cohen @DanaBerman9 @Yxp52492 Alex Rav-Acha @YHoshen

[Daniel Winter @_daniel_winter_]

🚀 Excited to share ObjectMate, our latest @GoogleAI project! A new approach to zero-shot subject-driven generation and object insertion.

🔗 Explore our project page: https://t.co/8ymD8QiiIT
📄 Arxiv: https://t.co/Mvdr4lY5Wk

[Daniel Winter @_daniel_winter_]

5/5 For object insertion, we leveraged an ObjectDrop (https://t.co/qqmKcCLsZP) data synthesis stage, where we remove objects with their shadows/reflections. This creates high-quality background images for supervised training, leading to SOTA results with either 1 or 3 references.

[Nataniel Ruiz @natanielruizg]

I'm sharing something unique we've been making at Google (w/ UNC). We are releasing our work on a new class of interactive experiences that we call generative infinite games, essentially video games where the game mechanics and graphics are fully subsumed by generative models 🧵

[Yossi Gandelsman @YGandelsman]

Giving a talk about common neurons in vision models and emergent representations in diffusion model weights today at @eccvconf ☺️

[Nataniel Ruiz @natanielruizg]

With friends at @Google we announce 💜 Magic Insert 💜 - a generative AI method that allows you to drag-and-drop a subject into an image with a vastly different style achieving a style-harmonized and realistic insertion of the subject (Thread 🧵)
web: https://t.co/lL7WYUqCDd