Angelos Assos

cs phd student @princeton

[Yuval Ran-Milo @YuvalRanMilo]

A sweet wrap-up to my visit at @Princeton: my work with @HazanPrinceton and Angelos Assos has been accepted to #NeurIPS2026! 🎉

We show how to learn linear dynamical systems with a small memory footprint. Here’s the idea 🧵

[Angelos Assos @assos98537672]

@lianegalanti Cool work Liane!😎

[Narutatsu Ri @narutatsuri]

New Paper: Do Thinking Tokens Help with Safety?

Reasoning models generate “thinking” tokens before answering, which improves performance on many tasks like math and coding.
A natural hope is that models can also use thinking to deliberate about whether to refuse or comply a request.
But how true is this?

We find a surprisingly sobering answer: current reasoning models often do not use thinking tokens for real safety deliberation.

Work with: Abhishek Panigrahi, @prfsanjeevarora at @PrincetonPLI

(More in 🧵below)

[Anand Brahmbhatt @AnandBrahm15501]

Excited to be at #ICLR2026 this week!

I’m presenting “A New Approach to Controlling Linear Dynamical Systems”, with my coauthors @gon_buzaglo , Sofiia Druchyna, and my advisor @HazanPrinceton.

📍 Pavilion 4 — Poster P4-#4503
🕒 Apr 23, 3:15–5:45 pm (Rio local time)

[Angelos Assos @assos98537672]

@YuvalRanMilo @Princeton @HazanPrinceton 🙌🙌

[Angelos Assos @assos98537672]

@lianegalanti @Princeton @HazanPrinceton @tri_dao 💪💪

[Ofir Press @OfirPress]

ChatGPT can solve novel, undergrad-level problems in *computational complexity* 🤯

"Please prove that the following problem is NP-hard..."

Solution in next tweet -->

Credit: @TzvikaGeft
(1/3)

[ONE PIECE スタッフ【公式】/ Official @Eiichiro_Staff]

Αγαπητέ άλτη από την Ελλάδα, Μιλτιάδη Τέντογλου:

Πραγματικά γιορτάζουμε και μεις, μαζί με τους φίλους μας ανά τον κόσμο. Νιώθουμε απεριόριστο σεβασμό για την προσπάθεια και τα επιτεύγματα σου!