Bonan Zhao / 赵博囡 retweetledi
🚀 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
English
Bonan Zhao / 赵博囡
141 posts
Bonan Zhao / 赵博囡
@BonanZhao
PI of the Computational Cognitive Science Lab at the School of Informatics, University of Edinburgh.
Katılım Aralık 2013
274 Takip Edilen743 Takipçiler
Bonan Zhao / 赵博囡 retweetledi
thank you @sopharicks for the fun interview, where I got to nerd about concepts, neologism, what interpretability looks like in the era of LLMs and many more! ❤️
Sophia@sopharicks
How do we know what machines know? How can we understand the new, emerging behavior of machines? In this conversation between @_beenkim from @GoogleDeepMind and the @buZZrobot community, we dug into the challenges of interpretability and explored how humans and machines can better understand each other. Watch the full discussion on our YouTube channel. Thank you, Been, for taking the time to talk to us! Timestamps: 0:00 Intro 0:18 AI teaches grandmasters chess 05:30 AI neologisms 10:17 Extracting knowledge from machines 13:43 Interpretability research 17:19 Are we keeping up with AI progress 18:34 New AI related terms 20:26 The right direction for interpretability 23:35 AI lying 27:49 Conseptual maps 30:30 AI researchers bias 33:33 Generalizing AI teaching humans 35:11 Is AI sentient 36:04 Does AI has concepts 41:53 Progress in machine understanding
English
Bonan Zhao / 赵博囡 retweetledi
Outstanding paper 🏆 1: Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling
openreview.net/forum?id=3BmPS…
English
Back at it! I'm happy to share that I joined DeepMind in London full-time, and I will be working on automated tools for neuroscientific discovery.
Disclaimer: I am not a go player, I just love this painting.
English
Are these openings for international students too
Bonan Zhao / 赵博囡@BonanZhao
My Lab at the University of Edinburgh🇬🇧 has funded PhD positions for this cycle! We study the computational principles of how people learn, reason, and communicate. It's a new lab, and you will be playing a big role in shaping its culture and foundations. Spread the words!
English
One of the most brilliant scientists in CogSci + one of the best institutions to study CogSci. 💫 Apply!!
Bonan Zhao / 赵博囡@BonanZhao
My Lab at the University of Edinburgh🇬🇧 has funded PhD positions for this cycle! We study the computational principles of how people learn, reason, and communicate. It's a new lab, and you will be playing a big role in shaping its culture and foundations. Spread the words!
English
Bonan Zhao / 赵博囡 retweetledi
🤖🧠 NEW PAPER ON COGSCI & AI 🧠🤖
Recent neural networks capture properties long thought to require symbols: compositionality, productivity, rapid learning
So what role should symbols play in theories of the mind? For our answer...read on!
Paper: arxiv.org/abs/2508.05776
1/n
English
My Lab at the University of Edinburgh🇬🇧 has funded PhD positions for this cycle!
We study the computational principles of how people learn, reason, and communicate.
It's a new lab, and you will be playing a big role in shaping its culture and foundations.
Spread the words!
English
Bonan Zhao / 赵博囡 retweetledi
I'll be joining the University of Hong Kong (at Asia's World City) as an Assistant Professor of Psychology this October, where I’ll be starting my own lab on machine-augmented cognition.
The lab aims to bridge AI and Cognitive Science to develop new theories and tools that can predict, explain, and ultimately shape the behavior of both humans and AI systems.
I'll be recruiting at all levels (PhDs, postdocs, interns, visiting students). Please feel free to DM if you're interested in joining.
English
Bonan Zhao / 赵博囡 retweetledi
Can an AI model predict perfectly and still have a terrible world model?
What would that even mean?
Our new ICML paper formalizes these questions
One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵
English
I recently defended my PhD thesis studying chunking in cognition and machine learning, working with Eric Schulz and Peter Dayan. @cpilab
Here is a summary of my studies during the years in Tuebingen.
English
Bonan Zhao / 赵博囡 retweetledi
Centaur may have learned a shortcut that explains away psychological tasks. @PsychBoyH
Link to preprint: osf.io/preprints/psya…
English
Bonan Zhao / 赵博囡 retweetledi
I’m recruiting PhD students to join the Computational Minds and Machines Lab at the University of Washington in Seattle! Join us to work at the intersection of computational cognitive science and AI with a broad focus on social intelligence. (Please reshare!)
English
Bonan Zhao / 赵博囡 retweetledi
New review on computational approaches to studying human planning out now in @TrendsCognSci! Really enjoyed having the opportunity to write something broader about the field with the help of @evanrussek @marcelomattar @weijima01 and @cocosci_lab cell.com/trends/cogniti…
English
Bonan Zhao / 赵博囡 retweetledi
It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods.
Ekdeep Singh Lubana@EkdeepL
🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient? Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵 1/
English
Bonan Zhao / 赵博囡 retweetledi
Thrilled to see our TinyRNN paper in @nature! We show how tiny RNNs predict choices of individual subjects accurately while staying fully interpretable. This approach can transform how we model cognitive processes in both healthy and disordered decisions. doi.org/10.1038/s41586…
English
Bonan Zhao / 赵博囡 retweetledi
Our paper on the logic of guesses is now out (w/ @NeilBramley and Chris Lucas).
We provide a new information-theoretic perspective on many phenomena (old and new) in judgment under uncertainty.
🧵
English
@Keremoktar @PsychPrinceton @Meta @real_asli @KelloggSchool @EliJFinkel @TaniaLombrozo Congrats! Dr Oktar rhymes so amazingly
English
🎉Life update🎉
After 6 wonderful years at @PsychPrinceton, I am officially *Dr.* Oktar!
Next: Postdoc @Meta FAIR studying LLM social cognition w/ @real_asli; then, postdoc @KelloggSchool studying disagreement w/ @EliJFinkel & Nour Kteily!
Thanks @TaniaLombrozo for the hood :)
English
Bonan Zhao / 赵博囡 retweetledi
📢 Abstract deadline extended (to rolling) for our conference on the Mathematics of Neuroscience and AI (Split, 27-30 May)
Thank you to everyone that has submitted so far! The quality is exceptional, and we are really excited to hear the latest results and theories!
We know many folks in the US have had delays, and we are doing everything we can to accommodate that.
Link in comments below:
English