Noam Rotstein

[Noam Rotstein @NoamRot]

📢📢📢 Check out our new paper!

We demonstrate how to control motion in any image-to-video model with no extra training.
Fast, simple, high-quality, and model-agnostic.

🔗 https://t.co/sMAeLL3Zc8

[Assaf Singer @assaf_singer]

We present Time-to-Move (TTM)! a training-free, plug-and-play method for precise motion control in video diffusion. Unlike prior training-based methods, TTM works with any backbone at no extra cost🔥

Page: https://t.co/gEPrwWwB7B
[1/4]
@NoamRot @orlitany @mann_amir_

[Noam Rotstein @NoamRot]

Exciting work tying image manipulation and brain modeling 🚀

[Navve wasserman @NavveW]

How can we tell whether a brain region causally represents a visual concept, rather than merely correlating with it?

Introducing BrainCause, a framework combining generative and brain models to create controlled stimuli and causally test neural representations.

More below 🧠👇

[Yoad Tewel @YoadTewel]

🎉 Happy to share our latest work: Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching (accepted to #ICML2026)!

TL;DR: We train image and video editing models without any paired data.

No ground-truth edit data, no external reward models.

[Shelly Golan @Shelly_Golan1]

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 🧵

[Noam Rotstein @NoamRot]

Happy to share that Time-to-Move has been accepted to @iclr_conf! 🇧🇷

It’s been exciting to see the community adopt this work over the past few months for enhancing control in video generation.

We’ll present it at the main conference this Friday, April 24, 10:30 AM–1:00 PM, and also at the ReALM-GEN workshop on April 27.

Feel free to stop by and say hi to me or @assaf_singer!

Thanks @_akhaliq for sharing our work!
Project page: https://t.co/hBSprg43rK

[AK @_akhaliq]

Time-to-Move

Training-Free Motion Controlled Video Generation via Dual-Clock Denoising

[Ido Sobol @IdoSobol]

Tired of 3D generations that look synthetic? They don’t have to.
Excited to share that Realiz3D is accepted to #CVPR2026 🎉
A framework for training diffusion models that are 3D-consistent, controllable, and photorealistic.
🔗 Project page: https://t.co/8UDsFk6N1A
🎥 Teaser ↓

[Narek Tumanyan @tnarek99]

Excited to present DRoPS! A novel method for dynamic 3D reconstruction from monocular videos, accompanied by a static-prescan of the dynamic object.

🌐 Project: https://t.co/rwIaAINSR4
📄 Paper: https://t.co/drNwUgetmK

🧵 [1/7]

[Noam Rotstein @NoamRot]

@HubermanSaar 🔥🔥

[Saar Huberman @HubermanSaar]

Excited to share that our work, “Image Generation from Contextually Contradictory Prompts,” was accepted to CVPR 2026 🎉

Diffusion models fail on some seemingly simple prompts.
Why do they ignore what you asked for?
We show why, and how to fix it with a simple, training-free method.

Joint work with @OPatashnik @OmerDahary @MokadyRon @DanielCohenOr1

[Saar Huberman @HubermanSaar]

SemanticMoments - Semantic motion similarity
How do you find videos with similar motion?
It’s harder than it sounds.
Models like VideoMAE and V-JEPA encode motion, but their embeddings are dominated by appearance.
So how do we build a compact embedding for motion similarity?
Joint work with @kfir99 @OPatashnik @BenaimSagie @MokadyRon

[Mickmumpitz @mickmumpitz]

The potential of this tech is just scratching the surface!

Watch this Blender layout transform into a final render using my Time-to-Move (TTM) workflow:

[Noam Rotstein @NoamRot]

🎭 CaricatureGS is out!

Check out how you can make photorealistic 3D caricatures from your 3DGS avatar!
Project page: https://t.co/c0teU7w8FQ

Led by @EldadMatmon with @amit_bracha and @RonnyKimmel.
Will be presented at @3DVconf (#3DV2026).

[enigmatic_e @8bit_e]

I wanted to try out @mickmumpitz ComfyUI workflow that lets you animate movement by manually shifting objects or images in the scene. Link to his tutorial below 👇

[Noam Rotstein @NoamRot]

Such a fun, creative use case of our Time-to-Move: driving motion from a crude real-world puppet. Looks amazing @mickmumpitz! 🚀

[Mickmumpitz @mickmumpitz]

For my real-life Toy Story short film, I built a workflow to control AI characters using puppets, paper cutouts, or animated previz!

And yeah I know… @CorridorDigital recently had a very similar idea. But they used a different technique!

Let’s compare👇

[Lumana @LumanaHQ]

This just in: Lumana is now the world’s fastest-growing AI video security company!

50,000 cameras surpassed in just over a year since emerging from stealth.

Read more: https://t.co/2Pj9e4cICD

#AIVideoSecurity #AI

[Navve wasserman @NavveW]

Thanks @rohanpaul_ai for sharing our new work!

Automatic Interpretability Pipeline + Human Brain Data = 🧠🔍🔥

See how we use a large-scale automatic interpretability pipeline to discover what concepts are represented in the human brain.

Page & Demo: https://t.co/3cStXhXs0b

[Noam Rotstein @NoamRot]

@AmitLinhard תרגום ישיר?

[derrick has started yet another project @dvsch]

I think Time to Move might be my favorite recent AI video tool, and I haven't seen a lot of talk about it. Maybe because it requires a lot of up front motion path generation? but it makes controllable video so much easier. 1st video is motion path provided, 2nd is output

[Nathan Shipley @CitizenPlain]

Playing with the Time To Move test monkey in ComfyUI. 🙃

Cool to see the little secondary and joint animation it adds #aivideo

[Noam Rotstein @NoamRot]

@CitizenPlain @assaf_singer Awesome example!

[saar stern @SternSaar]

🚀 Our paper “Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis” is accepted to 3DV 2026! @IdoSobol @orlitany
🔗 Project page: https://t.co/aNDh6y4XyS