yiftach edelstain

Researcher @DecartAI

[yiftach edelstain @Fortuneyiftah]

@Soloph0ne @justAnormalDudu @theomerb יש הרבה עדויות שכיסוי כזה יכול לגרום נזק למכשיר(תקלות מסך וכאלה, חום יתר וכו וכו). לפי הבנתי באפל לא ממליצים על כיסויים כאלה ללפטופ

[idan shenfeld @IdanShenfeld]

I’m flying tomorrow to Brazil for ICLR! 🇧🇷

If you’re into continual learning, self-distillation, learning from textual feedback, or just want to chat—let’s meet!

I'll be presenting the following papers:

[yiftach edelstain @Fortuneyiftah]

@RA0 @paoloanzn @ssslomp Ban users abusing their subscription plan? Are u intentionally being deft here?

[yiftach edelstain @Fortuneyiftah]

@KingOfLevant6 @ProudIsraeli4 טראמפ בתיקי אפשטיין גם אבל מה הפואנטה שלך?

[yiftach edelstain @Fortuneyiftah]

@BiniAshcknasy לא, כי אם היא הייתה נמנעת אז לוין היה טוען שהיא נמנעת כי היא יודעת שהיא אשמה, אין לברוח מהניסיון לרדוף אותה פה ביני די להיות תמים

[yiftach edelstain @Fortuneyiftah]

@DanaGat1 @ld69176781 @YairGolan1 מי שפונה אליך הוא ח״כ כרגע? כי יאיר גולן ראש רשימה שלא כולם חכ״ים אז אני לא בטוח שכולם מקבלים כסף מהמדינה או יותר מקושרים ממך בהכרח

[yiftach edelstain @Fortuneyiftah]

@BeYaron @TamerAm48431889 מי אמר לך שזה לא היה בהכנה מראש? מאיפה המודיעין שלך?

[yiftach edelstain @Fortuneyiftah]

@YiftachDayan @TamerAm48431889 לגיטימציה בינלאומית זה מטבע חסר ערך ב2026

[Or Litany @orlitany]

Excited to share our new paper, accepted to CVPR 2026: Instruct-Mix2Mix! 📢
We tackle the challenge of sparse multi-view editing: modifying a scene given only a few images (e.g., 4-8) via text instructions.
The code is available now.
Project page: https://t.co/61qC0Q4JJu
🧵

[Yoav HaCohen @yoavhacohen]

🚀 LTX-2 is now open source: text → audio + video.
Today we’re releasing LTX-2, the first open-source foundation model for joint audiovisual generation, together with a full technical report.
🧵👇

[yiftach edelstain @Fortuneyiftah]

@NogaArbell לכי לריב עם גרוק

[Decart @DecartAI]

Meet Lucy Motion - an image-to-video model with precise control over motion.

Instead of struggling to describe movement in text and hoping the model gets it right, you draw a path from a subject to its destination. Lucy animates it exactly along that path.

[Rohan Paul @rohanpaul_ai]

This paper uses AI-style interpretability tools to map which images trigger which visual concepts in the human brain.

It scales by adding about 120K extra images using predicted functional magnetic resonance imaging (fMRI) signals.

The problem is that fMRI data has about 40K voxels per person, each voxel is a tiny 3D pixel, and manual labeling does not scale.

The pipeline first breaks each brain region’s activity into patterns that can be mixed to rebuild any response, and a sparse autoencoder pushes each response to use only a few patterns.

For every pattern, it finds the top images that trigger it, captions those images, and has a model that writes text suggest shared meanings like “kitchen” or “hands in action”.

To avoid random labels, it builds a big concept list, marks each image as true or false for each concept, then keeps the concept that shows up most consistently in that pattern’s top images.

The payoff is a searchable map from image concepts to brain areas, plus a fair way to compare breakdown methods using held-out real scans.

----

Paper Link – arxiv. org/abs/2512.08560

Paper Title: "BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain"

[Decart @DecartAI]

Live from Vegas at re:Invent: AWS SVP Peter DeSantis jumps on stage and uses our Lucy-Edit model to turn himself into a cartoon version of AWS CTO Werner Vogel @werner @awscloud

[Decart @DecartAI]

Decart is pushing real-time visual intelligence forward.
Early access to Trainium3 helped us unlock 4× higher FPS and far more stable real-time video generation.

A new performance tier for our models.
https://t.co/btbpKNBQt9

[Decart @DecartAI]

Make quick, local edits to your video with Lucy-edit Fast.

Enjoy near Pro-level quality at 2× the speed and a fraction of the cost, bringing batch edits closer to real-time performance.

[yiftach edelstain @Fortuneyiftah]

Such a pleasure helping build Lucy-edit Fast — thrilled to get this into creators’ hands.

[Decart @DecartAI]

Make quick, local edits to your video with Lucy-edit Fast.

Enjoy near Pro-level quality at 2× the speed and a fraction of the cost, bringing batch edits closer to real-time performance.

[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

[yiftach edelstain @Fortuneyiftah]

@Itzikoi @TheAmazingRayu טעמתי, כן