Kozzy Voudouris
@kozzyvoudouris.bsky.social
AI | Cognitive Science | Linguistics
A great opportunity to work at the cutting edge of AI and cognitive science!
🚀 We are hiring! 🚀
🔍 Join us as a Postdoctoral Researcher (fully-funded) at the Helmholtz Institute for Human-Centered AI in Munich.
🔍 Join us as a Postdoctoral Researcher (fully-funded) at the Helmholtz Institute for Human-Centered AI in Munich.
November 3, 2025 at 10:28 AM
A great opportunity to work at the cutting edge of AI and cognitive science!
Reposted by Kozzy Voudouris
What influences whether people have fun with a task?
Our paper “Leveling up fun: learning progress, expectations and success influence enjoyment in video games” with @thecharleywu.bsky.social and @ericschulz.bsky.social now in Scientific Reports!
rdcu.be/eI069
Paper summary below 1/4
Our paper “Leveling up fun: learning progress, expectations and success influence enjoyment in video games” with @thecharleywu.bsky.social and @ericschulz.bsky.social now in Scientific Reports!
rdcu.be/eI069
Paper summary below 1/4
Leveling up fun: learning progress, expectations, and success influence enjoyment in video games
Scientific Reports - Leveling up fun: learning progress, expectations, and success influence enjoyment in video games
rdcu.be
October 2, 2025 at 9:32 AM
What influences whether people have fun with a task?
Our paper “Leveling up fun: learning progress, expectations and success influence enjoyment in video games” with @thecharleywu.bsky.social and @ericschulz.bsky.social now in Scientific Reports!
rdcu.be/eI069
Paper summary below 1/4
Our paper “Leveling up fun: learning progress, expectations and success influence enjoyment in video games” with @thecharleywu.bsky.social and @ericschulz.bsky.social now in Scientific Reports!
rdcu.be/eI069
Paper summary below 1/4
Reposted by Kozzy Voudouris
Happy to announce our paper got accepted to #NeurIPS!
@akjagadish.bsky.social @marvinmathony.bsky.social @ericschulz.bsky.social & Tobi Ludwig
arxiv.org/abs/2502.00879
@akjagadish.bsky.social @marvinmathony.bsky.social @ericschulz.bsky.social & Tobi Ludwig
arxiv.org/abs/2502.00879
Generating Computational Cognitive Models using Large Language Models
Computational cognitive models, which formalize theories of cognition, enable researchers to quantify cognitive processes and arbitrate between competing theories by fitting models to behavioral data....
arxiv.org
September 22, 2025 at 8:53 AM
Happy to announce our paper got accepted to #NeurIPS!
@akjagadish.bsky.social @marvinmathony.bsky.social @ericschulz.bsky.social & Tobi Ludwig
arxiv.org/abs/2502.00879
@akjagadish.bsky.social @marvinmathony.bsky.social @ericschulz.bsky.social & Tobi Ludwig
arxiv.org/abs/2502.00879
Reposted by Kozzy Voudouris
Excited for this paper to be out, literal years of hard work by Kozzy. Excitingly, my first last author paper!
This work came from joining the Kinds of Intelligence group at Cambridge and being given time by @martahalina.bsky.social to explore and cross disciplines. Hard work but very fun! 🧪 🤖🧠
This work came from joining the Kinds of Intelligence group at Cambridge and being given time by @martahalina.bsky.social to explore and cross disciplines. Hard work but very fun! 🧪 🤖🧠
We find that recurrence confers a significant advantage for learning more complex grammars, but lamination does not.
This work would not have been possible without Matishalin Patel, Colin Klein, Marta Halina, and Andrew Barron. You can check out our preprint here: arxiv.org/abs/2509.13968.
This work would not have been possible without Matishalin Patel, Colin Klein, Marta Halina, and Andrew Barron. You can check out our preprint here: arxiv.org/abs/2509.13968.
Exploring Major Transitions in the Evolution of Biological Cognition With Artificial Neural Networks
Transitional accounts of evolution emphasise a few changes that shape what is evolvable, with dramatic consequences for derived lineages. More recently it has been proposed that cognition might also h...
arxiv.org
September 18, 2025 at 5:04 PM
Excited for this paper to be out, literal years of hard work by Kozzy. Excitingly, my first last author paper!
This work came from joining the Kinds of Intelligence group at Cambridge and being given time by @martahalina.bsky.social to explore and cross disciplines. Hard work but very fun! 🧪 🤖🧠
This work came from joining the Kinds of Intelligence group at Cambridge and being given time by @martahalina.bsky.social to explore and cross disciplines. Hard work but very fun! 🧪 🤖🧠
A prominent idea in biology tells us that evolution is not always incremental, but often involves a few important structural changes that open up phylogenetic possibility.
Think: single cells ➡️ multicellular life. Solitary individuals ➡️ eusocial colonies.
Think: single cells ➡️ multicellular life. Solitary individuals ➡️ eusocial colonies.
September 18, 2025 at 10:45 AM
A prominent idea in biology tells us that evolution is not always incremental, but often involves a few important structural changes that open up phylogenetic possibility.
Think: single cells ➡️ multicellular life. Solitary individuals ➡️ eusocial colonies.
Think: single cells ➡️ multicellular life. Solitary individuals ➡️ eusocial colonies.
Doing cognitive science on non-human systems like animals or artificial intelligence, brings inherent challenges. One of them is generating plausible alternative explanations for behaviour that can be tested empirically.
September 2, 2025 at 8:37 AM
Doing cognitive science on non-human systems like animals or artificial intelligence, brings inherent challenges. One of them is generating plausible alternative explanations for behaviour that can be tested empirically.
Reposted by Kozzy Voudouris
Excited to say our paper got accepted to ICML! We added new findings including this: models fine-tuned on a visual counterfactual reasoning task do not generalize to the underlying factual physical reasoning task, even with test images matched to the fine-tuning data set.
June 2, 2025 at 7:45 AM
Excited to say our paper got accepted to ICML! We added new findings including this: models fine-tuned on a visual counterfactual reasoning task do not generalize to the underlying factual physical reasoning task, even with test images matched to the fine-tuning data set.
I am very pleased to announce that my paper "Morgan's Canon and the Associative-Cognitive Distinction Today: A Survey of Practitioners" was published this week in the Journal of Comparative Psychology.
May 23, 2025 at 8:03 AM
I am very pleased to announce that my paper "Morgan's Canon and the Associative-Cognitive Distinction Today: A Survey of Practitioners" was published this week in the Journal of Comparative Psychology.
Reposted by Kozzy Voudouris
Bringing comparative cognition approaches to AI systems
Comment by Konstantinos Voudouris (@kozzyvoudouris.bsky.social), Lucy Cheke (@lucycheke.bsky.social) & Eric Schulz (@ericschulz.bsky.social)
go.nature.com/43djJlv
Comment by Konstantinos Voudouris (@kozzyvoudouris.bsky.social), Lucy Cheke (@lucycheke.bsky.social) & Eric Schulz (@ericschulz.bsky.social)
go.nature.com/43djJlv
May 13, 2025 at 3:03 PM
Bringing comparative cognition approaches to AI systems
Comment by Konstantinos Voudouris (@kozzyvoudouris.bsky.social), Lucy Cheke (@lucycheke.bsky.social) & Eric Schulz (@ericschulz.bsky.social)
go.nature.com/43djJlv
Comment by Konstantinos Voudouris (@kozzyvoudouris.bsky.social), Lucy Cheke (@lucycheke.bsky.social) & Eric Schulz (@ericschulz.bsky.social)
go.nature.com/43djJlv
Reposted by Kozzy Voudouris
Tired but happy to say this is out w @andreaeyleen.bsky.social: Are Neurocognitive Representations 'Small Cakes'? philsci-archive.pitt.edu/24834/
We analyse cog neuro theories showing how vicious regress, e.g. the homunculus fallacy, is (sadly) alive and well — and importantly how to avoid it. 1/
We analyse cog neuro theories showing how vicious regress, e.g. the homunculus fallacy, is (sadly) alive and well — and importantly how to avoid it. 1/
March 1, 2025 at 2:16 PM
Tired but happy to say this is out w @andreaeyleen.bsky.social: Are Neurocognitive Representations 'Small Cakes'? philsci-archive.pitt.edu/24834/
We analyse cog neuro theories showing how vicious regress, e.g. the homunculus fallacy, is (sadly) alive and well — and importantly how to avoid it. 1/
We analyse cog neuro theories showing how vicious regress, e.g. the homunculus fallacy, is (sadly) alive and well — and importantly how to avoid it. 1/
How can we rigorously investigate the common-sense capabilities of agentic AI systems? How can we build better models of non-human animal cognition?
(Re-)introducing the Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research!
(Re-)introducing the Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research!
March 1, 2025 at 11:06 AM
How can we rigorously investigate the common-sense capabilities of agentic AI systems? How can we build better models of non-human animal cognition?
(Re-)introducing the Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research!
(Re-)introducing the Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research!
Reposted by Kozzy Voudouris
New preprint! In arxiv.org/abs/2502.20349 “Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior” we synthesize AI & cognitive science works to a perspective on seeking generalizable understanding of cognition. Thread:
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior
Artificial Intelligence increasingly pursues large, complex models that perform many tasks within increasingly realistic domains. How, if at all, should these developments in AI influence cognitive sc...
arxiv.org
February 28, 2025 at 5:14 PM
New preprint! In arxiv.org/abs/2502.20349 “Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior” we synthesize AI & cognitive science works to a perspective on seeking generalizable understanding of cognition. Thread:
Reposted by Kozzy Voudouris
Every experience is unique 🌟 light shifts, angles change, yet we recognize objects effortlessly. How do our minds do this? And (how) do they differ from machines? In our new preprint with @ericschulz.bsky.social, we review human generalization and compare it to machine generalization: osf.io/k6ect
February 28, 2025 at 1:01 PM
Every experience is unique 🌟 light shifts, angles change, yet we recognize objects effortlessly. How do our minds do this? And (how) do they differ from machines? In our new preprint with @ericschulz.bsky.social, we review human generalization and compare it to machine generalization: osf.io/k6ect
Reposted by Kozzy Voudouris
About a month late posting this, but here's a new project with @ericschulz.bsky.social, @akjagadish.bsky.social, @marvinmathony.bsky.social and Tobias Ludwig
We are using LLMs to propose cognitive models in learning and decision making data. Presenting this work at RLDM!
arxiv.org/abs/2502.00879
We are using LLMs to propose cognitive models in learning and decision making data. Presenting this work at RLDM!
arxiv.org/abs/2502.00879
Towards Automation of Cognitive Modeling using Large Language Models
Computational cognitive models, which formalize theories of cognition, enable researchers to quantify cognitive processes and arbitrate between competing theories by fitting models to behavioral data....
arxiv.org
February 26, 2025 at 10:08 AM
About a month late posting this, but here's a new project with @ericschulz.bsky.social, @akjagadish.bsky.social, @marvinmathony.bsky.social and Tobias Ludwig
We are using LLMs to propose cognitive models in learning and decision making data. Presenting this work at RLDM!
arxiv.org/abs/2502.00879
We are using LLMs to propose cognitive models in learning and decision making data. Presenting this work at RLDM!
arxiv.org/abs/2502.00879
Reposted by Kozzy Voudouris
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:
February 25, 2025 at 10:45 AM
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: