Raja Giryes

Professor of Electrical and Computer Engineering at Tel Aviv University. On Sabbatical at Apple AI Research. Interested in AI, multimodal and signal processing

[Raja Giryes @RGiryes]

I’m excited to be spending my sabbatical at #Apple, collaborating with Vladlen Koltun and the team on a range of cutting-edge AI projects. Looking forward to this new chapter!

[Raja Giryes @RGiryes]

@yoavgo When you supervise students, the accepted papers (for the good and the bad of it) are quite important for their future career either in academy or industry. So at least on my end, the excitement is for the students as I know how important it is for them

[Raja Giryes @RGiryes]

@ChrSzegedy I personally think that any arxiv submission should receive an AI review and the authors should decide if they still post their paper given the review or first revise and then submit with their answer to the review. Will fix a lot of slops

[Raja Giryes @RGiryes]

@yoavgo Yup. That what I meant 🧲

[AK @_akhaliq]

Video Analysis and Generation via a Semantic Progress Function

paper: https://t.co/VKB64av2ZC

[Sagi Polaczek 🦜 @PolaczekSagi]

with the Semantic Progress Function (SPF) you can MEASURE the semantic change.

so, is GPT-Image-2 good enough? 👀
https://t.co/Eo0MYx5bIj

[Sagi Polaczek 🦜 @PolaczekSagi]

fresh out of the oven 🔥✨

see the two videos below? with the 'Semantic Progress Function' (SPF) you can finally ANALYSE (and control!) the semantic progression of First-to-Last-Frame video generation.

[Gal Metzer @galmetz]

Excited to share our work accepted to #SIGGRAPH2026 ! Video generation models struggle with something few talk about: their transformations don't evolve smoothly. You get long boring stretches... then a sudden semantic jump where everything "catches up" at once.

[Garry Tan @garrytan]

Happy Easter. He is risen.

[Raja Giryes @RGiryes]

@yoavgo לא דברים שאי אפשר להוכיח על שיטות אחרות. וגם ההנחות היו לא סבירות כמו רוחב אינסופי וכו׳. אבל לרשתות כן יש את המוטיבציה הביולוגית שזה לפי דעתי בסיס הרבה יותר חזק.

[Noa Kraicer @NKraicer]

Our paper Guided Lensless Polarization Imaging was accepted to #CVPR2026 (Findings) 🎉📸

[Ben Lipkin @ben_lipkin]

super excited this it out! lots of fun insights, tips, and tricks on how all parts of the RL stack, from policy gradient in general, to policy staleness, to clipping, to numerics, all modulate entropy + some principled control strategies to stabilize!

[Aleksei Petrenko @petrenko_ai]

Our ICLR 2026 paper "Entropy-Preserving Reinforcement Learning" is now on arXiv.

We strike at one of the core RL issues: exploration in action space.
We study why token distribution entropy collapses in LLM post-training preventing further exploration and we propose fixes!

[Nimrod Shabtay @NimrodShabtay]

Introducing Look Where It Matters — High-Resolution Crops Retrieval for Efficient VLMs.
VLMs don't need to process full high-res images. AwaRes uses tool-calling to retrieve only the high-res regions needed to answer a given query🧵
https://t.co/JCiHCykcRP https://t.co/xqIYzmKeHP

[Moran Yanuka @moranynk]

🎙️ Introducing ID-LoRA: the first open-source model to jointly generate a video with a person's appearance and voice in a single pass from just a reference image + short audio clip. No more cascaded pipelines where the audio can't follow your prompt.

https://t.co/AZu9FfbzWG

[Raja Giryes @RGiryes]

@docmilanfar I would try PNAS

[Raja Giryes @RGiryes]

@yoavgo דרך אגב, אנחנו מגייסים בחשמל. בהינתן שמדמ״ח גמור אתה מוזמן לעבור 😅

[Raja Giryes @RGiryes]

@yoavgo ראה ערך אל תכשירו יותר רדיולוגים…

[Raja Giryes @RGiryes]

@yoavgo כרגע כל דבר שמערב חומרה. אבל להגיד איפה קשה במיוחד זה טריקי. לפני עשור חשבנו שרדיולוגיה פתור וקידוד זה בעיה הרבה יותר קלה והיום זה מתהפך. אז בסופו של יום מה באמת קשה זה עניין של תפישה ומה אנחנו יודעים לעשות עם הכלים של היום