Omri Fahn

[Mor Geva @megamor2]

3 papers accepted at #ICML2026 🇰🇷🎉

🔸 From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
https://t.co/uSkeXBhmqe

🔸 Interpretability can be Actionable
https://t.co/SeoKTd3Bff

🔸Hallucinations Undermine Trust; Metacognition is a Way Forward (out soon) @_galyo @ymatias

Congrats to all collaborators!

[Omri Fahn @OmriFahn]

MFA is a beautiful visualization, but not only that.
It’s a practical tool:
competitive localization and better steering, while revealing that concepts live in regions, not just single directions.

Grateful I got to contribute to this with an awesome team!

[Or Shafran @OrShafran]

It's time to look past dictionary learning for decomposing LM activations.

What happens when we instead leverage local geometry?

We find a natural region-based decomposition that yields better steering and localization 🧵 1/

[Omri Fahn @OmriFahn]

@MayaKidon נסי את זה, עובד כמו קסם

[Omri Fahn @OmriFahn]

Honored to see Formula Completion highlighted by @satyanadella 🎉

Proud to be part of the incredible team bringing this to life at Microsoft Excel!

[Omri Fahn @OmriFahn]

@MayaKidon בשם אקסל, תודה בחזרה ;)

[Omri Fahn @OmriFahn]

Honored to see Formula Completion highlighted by @satyanadella 🎉

Proud to be part of the incredible team bringing this to life at Microsoft Excel!

[Satya Nadella @satyanadella]

This is super useful! With new Formula Completions in Excel, just type "=" and Copilot proactively suggests a formula, based on the context of your sheet. Here's a great example.

[Satya Nadella @satyanadella]

This is super useful! With new Formula Completions in Excel, just type "=" and Copilot proactively suggests a formula, based on the context of your sheet. Here's a great example.

[Omri Fahn @OmriFahn]

🤔 Can an LLM sense it's about to hallucinate—before it speaks?
🤔 And do those gut feelings live inside its geometry?

Thrilled to share our new paper:
“Pre-trained LLMs Learn Multiple Types of Uncertainty”
(Cohen • Fahn • de Melo, 2025)
📄 https://t.co/XbAc6udvbW

[Omri Fahn @OmriFahn]

🤔Can an LLM "unconscious" feel a lie bubbling up before it speaks?
🤔And what mysteries hide in its linear space of uncertainty?
Thrilled to share our new paper:
“Pre-trained LLMs Learn Multiple Types of Uncertainty” (@roicohen9•@OmriFahn•@GerardDeMelo)
https://t.co/XbAc6ucXmo

[Omri Fahn @OmriFahn]

8/
📄 Read the full paper:
https://t.co/XbAc6ucXmo
Thanks for reading!

#AI #LLM #Uncertainty #Interpretability #Research

[Omri Fahn @OmriFahn]

7/
🎙️ Prefer a quick listen?
• English NotebookLM podcast (8 min):
https://t.co/OzrquQGUur
• Hebrew NotebookLM podcast:
https://t.co/bVHsfltPMD

[arXiv Sound @ArxivSound]

``NAST: Noise Aware Speech Tokenization for Speech Language Models,'' Shoval Messica, Yossi Adi, https://t.co/J1smUHwR3y

[Shoval Messica @ShovalMessica]

🚨I’m excited to share our #INTERSPEECH2024 paper "NAST: Noise Aware Speech Tokenization for Speech Language Models” 🥳 W/ @adiyossLC
Paper-https://t.co/olTARW7ckc
Code-https://t.co/SeuW6KkaVB

[Omri Fahn @OmriFahn]

https://t.co/ccxKCF1QFB

[Omri Fahn @OmriFahn]

Hello Berliners, tired of hunting for the perfect apartment or sublet? As a former exchange student in Berlin, I understand the struggle! So, I decided to let AI do the hard work.

https://t.co/ccxKCF2ov9

[Omri Fahn @OmriFahn]

Our platform is really simple to use, quicker to use than the time it takes to read this post 😉

May the AI-Gesucht guide you to your dream apartment Inside of Berlin’s ring 💍 !