Can Demircan

phd student @cpilab working on machine learning/cognitive science

[Marcel Binz @marcel_binz]

📢 The CORE COGNITION lab (https://t.co/LJBwOPghoe) is looking to hire another PhD student, working on automated scientific discovery and knowledge representation in cognitive science.

Starting date: March to September 2027.

🙏 Please share widely!

[Can Demircan @can_demircann]

Alireza is both an amazing scientist and a great person. go apply now!

[Alireza Modirshanechi @modirshanechi]

Excited to share that I'll be starting as a junior professor and Emmy Noether awardee at the University of Göttingen this October! 🥳

🚀 I'll be hiring PhD students and postdocs across both ML and CogSci: https://t.co/SWO5gf4Y57

Please spread the word! 🙏

[Helmholtz Institute for Human-Centered AI @cpilab]

We are looking for a postdoctoral researcher who wants to innovate at the intersection of cognitive science, neuroscience, and machine learning.
📍Munich
📅Flexible start: 10/2026–03/2027
⏳Full consideration by 14/08/2026
💼Funded for 2 years, extension possible
Please share.

[Tankred Saanum @TankredSaanum]

Thrilled to finally share some of the work we at @Recursive_SI has been doing since we launched!🔥

We've made a system that autonomously conducts AI research and tested it across three different settings: Small Language Model training, NanoGPT speedrunning, and kernel engineering!

A bit like Karpathy's Autoresearch, but scaled up and designed to be open-ended, we can push our system to optimize models, training algorithms, and kernels in really cool ways.

Blogpost:
https://t.co/Ys7W3MJJqi

[Marcel Binz @marcel_binz]

Excited to announce that I'll be starting my own lab in Tübingen this October!

Hiring at all levels: Postdoc, PhD & RA.

Want to work on computational cognitive science at scale? Apply: https://t.co/cGX9UfVjwo

Reposts and shares much appreciated 🙏

[Helmholtz Institute for Human-Centered AI @cpilab]

🚀 We are hiring! 🚀

🔍 Join us as a Postdoctoral Researcher (fully-funded) at the Helmholtz Institute for Human-Centered AI in Munich.
@HelmholtzMunich @helmholtz_ai @ELLISforEurope

[Alireza Modirshanechi @modirshanechi]

New in @PNASNews: https://t.co/95Gs0QTYf4

We study how humans explore a 61-state environment with a stochastic region that mimics a “noisy-TV.”

Results: Participants keep exploring the stochastic part even when it’s unhelpful, and novelty-seeking best explains this behavior.

[Can Demircan @can_demircann]

Turns out some induction heads are very good at learning hierarchical sequences. Check out our work below on the mechanisms behind this!

[Tankred Saanum @TankredSaanum]

Induction heads are surprisingly powerful. In a new preprint, we find that they can learn what to attend to in-context! We study this in a hierarchical prediction task and uncover a possible mechanism giving rise to in-context learning in induction heads. See thread for details!

[Luca Schulze Buschoff @lucaschubu]

In previous work we found that VLMs fall short of human visual cognition. To make them better, we fine-tuned them on visual cognition tasks. We find that while this improves performance on the fine-tuning task, it does not lead to models that generalize to other related tasks:

[Luca Schulze Buschoff @lucaschubu]

Happy to say we made the cover too! (@elifakata, @cpilab)

[Tankred Saanum @TankredSaanum]

Super happy that this has been accepted to @iclr_conf !

Me and @can_demircann will be there to talk about what we can learn about in-context learning using SAEs

See you in Singapore 🇸🇬

[Can Demircan @can_demircann]

Many thanks to @TankredSaanum @LeonardoPettini @marcel_binz @doellerlab @mona_garvert @cpilab

Check out the paper here: https://t.co/8ZvfRcKVEj

Please reach out if you're at NeurIPS and wanna talk about representational alignment, mechanistic interpretability, or CogSci!

[Can Demircan @can_demircann]

Alignment is more than comparing similarity judgments! How well do pretrained neural networks align with humans in few-shot learning settings? Come check our poster #3904 at #NeurIPS on Wednesday to find out

[Can Demircan @can_demircann]

Lastly, we found that previously established alignment methods do not consistently yield better results compared to non-aligned baselines.

[Tankred Saanum @TankredSaanum]

Super excited to be going to #NeurIPS to present new work on softly state-invariant world models! We introduce an info bottleneck making world models represent action effects more consistently in latent space, improving prediction and planning! Reach out if you want to meet!

[Alireza Modirshanechi @modirshanechi]

🚨Preprint alert🚨

In an amazing collaboration with @GruazL53069, @sobeckerneuro, & J Brea, we explored a major puzzle in neuroscience & psychology:

*What are the merits of curiosity⁉️*
https://t.co/Au2HxPbZQL

1/7