Federico Adolfi
@fedeadolfi.bsky.social
Computation & Complexity | AI Interpretability | Meta-theory | Computational Cognitive Science
https://fedeadolfi.github.io
https://fedeadolfi.github.io
Pinned
Federico Adolfi
@fedeadolfi.bsky.social
· Apr 18
I will be presenting this ✨ spotlight 💫 paper at #ICLR2025 with @martinagvilas.bsky.social. Come say hi if you're interested in DNN circuits, complexity and #interpretability
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
📆 Poster Session 4 (#530)
🕰️ Fri 25 Apr. 3:00-5:30 PM
📝 openreview.net/forum?id=Qog...
📊 iclr.cc/virtual/2025...
Documentary filmmakers: the thing that makes these documentaries special is that you can hear the stories directly from the mouths of those who experienced these remarkable events
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
October 25, 2025 at 2:08 PM
Documentary filmmakers: the thing that makes these documentaries special is that you can hear the stories directly from the mouths of those who experienced these remarkable events
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
Also DFs: have a seat, you’ll be looking at the camera, here’s the script, stick to it, those exact words
Reposted by Federico Adolfi
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
October 20, 2025 at 7:55 AM
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
October 20, 2025 at 7:55 AM
In what can only be described as one of my most spectacular failures of social inference, someone sitting next to me at the movie theatre asked me ‘what movie is this?’, I told them, then I thought about it for a moment and asked them politely how come they didn’t know what movie they came to see.
Reposted by Federico Adolfi
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
October 17, 2025 at 12:26 PM
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
October 17, 2025 at 12:26 PM
Me: I developed a chemistry of lemon gooey butter cookies. It took many attempts but I managed to master the rationale, technique and execution, and today it is my pleasure to show you the result
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Them: did you finally decide to just follow the recipe closely this time?
Me:
Me: to the letter
Reposted by Federico Adolfi
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
October 15, 2025 at 8:24 AM
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
October 15, 2025 at 8:24 AM
Many character quirks make a lot more sense when you realize everyone in the show is playing ‘the floor is lava except for predefined marks’
Reposted by Federico Adolfi
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
October 8, 2025 at 7:27 PM
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
Reposted by Federico Adolfi
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
October 7, 2025 at 9:40 AM
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
October 7, 2025 at 9:40 AM
**Me at a Halloween party**
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Them, looking at my costume: what are you supposed to be?
Me: that’s a great question! Let’s think about it carefully step by step. You’re asking about my costu—
Them: no stop it
Reposted by Federico Adolfi
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
September 17, 2025 at 8:09 AM
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
September 17, 2025 at 8:09 AM
Is there a sudden increase in the number of job ads from psych / cogsci departments looking for people “integrating AI in their work”? It’s usually so poorly justified you can read desperation between the lines
Reposted by Federico Adolfi
Why does Western Paleolithic cave art strongly prefer animal side views and often use abbreviations? Our new paper in Topics in Cognitive Science challenges long-held assumptions about these artistic choices using cognitive science experiments. A thread 1/n
onlinelibrary.wiley.com/doi/10.1111/...
onlinelibrary.wiley.com/doi/10.1111/...
September 15, 2025 at 2:41 PM
Why does Western Paleolithic cave art strongly prefer animal side views and often use abbreviations? Our new paper in Topics in Cognitive Science challenges long-held assumptions about these artistic choices using cognitive science experiments. A thread 1/n
onlinelibrary.wiley.com/doi/10.1111/...
onlinelibrary.wiley.com/doi/10.1111/...
We had a brief moment where mathematical model, domain theory, experiment and simulation all fit together beautifully…
and then we had to go double checking things like we have a death wish
We broke it.
AND THEN WE FIXED IT IMMEDIATELY AND IT WORKS
😎
and then we had to go double checking things like we have a death wish
We broke it.
AND THEN WE FIXED IT IMMEDIATELY AND IT WORKS
😎
a man in a suit and white shirt is sitting in front of a purple curtain and holding a glass of water .
Alt: a man in a suit and white shirt is sitting in front of a purple curtain and holding a glass of water trying to take a sip but his hand is shaking too much
media.tenor.com
August 27, 2025 at 6:45 PM
We had a brief moment where mathematical model, domain theory, experiment and simulation all fit together beautifully…
and then we had to go double checking things like we have a death wish
We broke it.
AND THEN WE FIXED IT IMMEDIATELY AND IT WORKS
😎
and then we had to go double checking things like we have a death wish
We broke it.
AND THEN WE FIXED IT IMMEDIATELY AND IT WORKS
😎
Reposted by Federico Adolfi
𝗪𝗵𝗮𝘁'𝘀 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗶𝘀 𝗶𝘁 𝗲𝗺𝗲𝗿𝗴𝗲𝗻𝘁?
Don't miss the Neuroscience and Philosophy Salon.
Earl Miller and team will discuss recent paper and we'll have plenty of discussion. Open to all.
Sept 12, noon EST-US
umd.zoom.us/meeting/regi...
#neuroskyence
@earlkmiller.bsky.social
Don't miss the Neuroscience and Philosophy Salon.
Earl Miller and team will discuss recent paper and we'll have plenty of discussion. Open to all.
Sept 12, noon EST-US
umd.zoom.us/meeting/regi...
#neuroskyence
@earlkmiller.bsky.social
August 24, 2025 at 4:06 PM
𝗪𝗵𝗮𝘁'𝘀 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗶𝘀 𝗶𝘁 𝗲𝗺𝗲𝗿𝗴𝗲𝗻𝘁?
Don't miss the Neuroscience and Philosophy Salon.
Earl Miller and team will discuss recent paper and we'll have plenty of discussion. Open to all.
Sept 12, noon EST-US
umd.zoom.us/meeting/regi...
#neuroskyence
@earlkmiller.bsky.social
Don't miss the Neuroscience and Philosophy Salon.
Earl Miller and team will discuss recent paper and we'll have plenty of discussion. Open to all.
Sept 12, noon EST-US
umd.zoom.us/meeting/regi...
#neuroskyence
@earlkmiller.bsky.social
Reposted by Federico Adolfi
In our forthcoming paper, John Hummel and I ask what it would mean for a neural computing architecture such as a brain to implement a symbol system, and the related question of what makes it difficult for them to do so, with an eye toward the differences between humans, animals, and ANNs.
From Basic Affordances to Symbolic Thought: A Computational Phylogenesis of Biological Intelligence
What is it about human brains that allows us to reason symbolically whereas most other animals cannot? There is evidence that dynamic binding, the ability to combine neurons into groups on the fly, is...
arxiv.org
August 22, 2025 at 6:25 PM
In our forthcoming paper, John Hummel and I ask what it would mean for a neural computing architecture such as a brain to implement a symbol system, and the related question of what makes it difficult for them to do so, with an eye toward the differences between humans, animals, and ANNs.
Reposted by Federico Adolfi
What is it about human brains that allows us to reason symbolically whereas most other animals cannot? And why does AI sometimes struggle to generate images of objects in statistically unusual spatial relationships to each other, when people wouldn’t struggle to imagine such relationships?
August 22, 2025 at 6:24 PM
What is it about human brains that allows us to reason symbolically whereas most other animals cannot? And why does AI sometimes struggle to generate images of objects in statistically unusual spatial relationships to each other, when people wouldn’t struggle to imagine such relationships?
Stop whatever you’re doing and run — don’t walk — and get yourself a copy of this foundational scroll and then read the shit out of it
What is it about human brains that allows us to reason symbolically whereas most other animals cannot? And why does AI sometimes struggle to generate images of objects in statistically unusual spatial relationships to each other, when people wouldn’t struggle to imagine such relationships?
August 22, 2025 at 6:56 PM
Stop whatever you’re doing and run — don’t walk — and get yourself a copy of this foundational scroll and then read the shit out of it
I just discovered (the hard way) that having a fruit salad before drinking tonic water makes the latter taste like airplane toilet
August 6, 2025 at 2:50 AM
I just discovered (the hard way) that having a fruit salad before drinking tonic water makes the latter taste like airplane toilet
Reposted by Federico Adolfi
@laurennross.bsky.social is giving an important reminder of the importance of philosophy of science in cognitive science at the #cogsci2025 keynote, which I really appreciate in the current moment.
August 2, 2025 at 4:23 PM
@laurennross.bsky.social is giving an important reminder of the importance of philosophy of science in cognitive science at the #cogsci2025 keynote, which I really appreciate in the current moment.
Reposted by Federico Adolfi
Me: hi sorry I think I left my keycard in my room
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
August 2, 2025 at 2:13 AM
Me: hi sorry I think I left my keycard in my room
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
Me: hi sorry I think I left my keycard in my room
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
August 2, 2025 at 2:13 AM
Me: hi sorry I think I left my keycard in my room
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
Front desk guy: no problem sir what’s your room number
Me: I think I forgot my room number
Guy: can I have some id
Me: look we can do this all day
Reposted by Federico Adolfi
1
To predict the behaviour of a primate, would you rather base your guess on a closely related species or one with a similar brain shape? We looked at brains & behaviours of 70 species, you’ll be surprised!
🧵Thread on our new preprint with @r3rt0.bsky.social , doi.org/10.1101/2025...
To predict the behaviour of a primate, would you rather base your guess on a closely related species or one with a similar brain shape? We looked at brains & behaviours of 70 species, you’ll be surprised!
🧵Thread on our new preprint with @r3rt0.bsky.social , doi.org/10.1101/2025...
July 27, 2025 at 5:26 PM
1
To predict the behaviour of a primate, would you rather base your guess on a closely related species or one with a similar brain shape? We looked at brains & behaviours of 70 species, you’ll be surprised!
🧵Thread on our new preprint with @r3rt0.bsky.social , doi.org/10.1101/2025...
To predict the behaviour of a primate, would you rather base your guess on a closely related species or one with a similar brain shape? We looked at brains & behaviours of 70 species, you’ll be surprised!
🧵Thread on our new preprint with @r3rt0.bsky.social , doi.org/10.1101/2025...
Reposted by Federico Adolfi
📣 Life update: Thrilled to announce that I’ll be starting as faculty at the Max Planck Institute for Software Systems this Fall!
I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html
I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html
July 22, 2025 at 4:12 AM
📣 Life update: Thrilled to announce that I’ll be starting as faculty at the Max Planck Institute for Software Systems this Fall!
I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html
I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html
Reposted by Federico Adolfi
Excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
Home
First Workshop on Interpreting Cognition in Deep Learning Models (NeurIPS 2025)
coginterp.github.io
July 16, 2025 at 1:08 PM
Excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4