Abdulkadir Gokce

🎉 Re-Align is back for its 4th edition at ICLR 2026! 📣 We invite submissions on representational alignment, spanning ML, Neuroscience, CogSci, and related fields. 📝 Tracks: Short (≤5p), Long (≤10p), Challenge (blog) ⏰ Feb 5, 2026 for papers 🔗 representational-alignment.github.io/2026/

🧠 New preprint: we show that model-guided microstimulation can steer monkey visual behavior. Paper: arxiv.org/abs/2510.03684 🧵

🦾🧠 New Preprint!! What happens if we induce dyslexia in vision–language models? By ablating VWFA-analogous units, we show that models reproduce selective reading impairments similar to human dyslexia. 📄 doi.org/10.48550/arXiv…

🧠 NEW PREPRINT Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective biorxiv.org/content/10.110…

🚨New Preprint!! Thrilled to share with you our latest work: “Mixture of Cognitive Reasoners”, a modular transformer architecture inspired by the brain’s functional networks: language, logic, social reasoning, and world knowledge. 1/ 🧵👇

AI vision is insanely good nowadays—but is it really like human vision or something else entirely? In our new pre-print, we pinpoint a fundamental visual mechanism that's trivial for humans yet causes most models to fail spectacularly. Let's dive in👇🧠 [arxiv.org/abs/2504.05253]

🚨 New Preprint!! LLMs trained on next-word prediction (NWP) show high alignment with brain recordings. But what drives this alignment—linguistic structure or world knowledge? And how does this alignment evolve during training? Our new paper explores these questions. 👇🧵

🚨 New Paper! Can neuroscience localizers uncover brain-like functional specializations in LLMs? 🧠🤖 Yes! We analyzed 18 LLMs and found units mirroring the brain's language, theory of mind, and multiple demand networks! w/ @GretaTuckute, @ABosselut, & @martin_schrimpf 🧵👇

🚨 New Paper!! How can we train LLMs using 100M words? In our @babyLMchallenge paper, we introduce a new self-synthesis training recipe to tackle this question! 🍼💻 This was a fun project co-led by me, @yingtian80536, @akgokce0, w/ @HannesMehrer & @martin_schrimpf 🧵⬇️

7/7 All code and over 600 model checkpoints are open-source: github.com/epflneuroailab…

6/7 An interesting disconnect: While models can increasingly match human behavior through scaling, they hit a wall when trying to match how the brain processes information. This suggests fundamental limitations in current AI architectures.

Excited to share our latest preprint on scaling laws in primate vision modeling! We trained and analyzed 600+ neural networks to understand how bigger models & more data affect brain predictivity. Paper: arxiv.org/abs/2411.05712… By me & @martin_schrimpf at @EPFL_en @ICepfl