danilobzdok
@danilobzdok.bsky.social
Research director | @McGillU @Mila_Quebec @IVADO_Qc | My team designs machine learning frameworks to understand biological systems from new angles of attack
Our paper at #NeurIPS 2025:
1) Pre-trained transformer models impose semantic structure on inputs.
2) More skewing of transformer processing as input uncertainty increases.
3) Spurious concept activations can predict hallucinations.
arxiv.org/pdf/2509.069...
#large #language #models + #safety
1) Pre-trained transformer models impose semantic structure on inputs.
2) More skewing of transformer processing as input uncertainty increases.
3) Spurious concept activations can predict hallucinations.
arxiv.org/pdf/2509.069...
#large #language #models + #safety
September 19, 2025 at 2:43 PM
📢 job opening: software developer at Mila Quebec AI Institute & McGill
As of now, my team is looking to hire a new technical staff member with abackground in a STEM area for running and curating existing AI analysis pipelines, as well as designing GUIs around them.
Please DM or email me, with CV
As of now, my team is looking to hire a new technical staff member with abackground in a STEM area for running and curating existing AI analysis pipelines, as well as designing GUIs around them.
Please DM or email me, with CV
July 28, 2025 at 8:21 PM
📢 job opening: software developer at Mila Quebec AI Institute & McGill
As of now, my team is looking to hire a new technical staff member with abackground in a STEM area for running and curating existing AI analysis pipelines, as well as designing GUIs around them.
Please DM or email me, with CV
As of now, my team is looking to hire a new technical staff member with abackground in a STEM area for running and curating existing AI analysis pipelines, as well as designing GUIs around them.
Please DM or email me, with CV
Reposted by danilobzdok
1/11 Excited to share our @Naturestudy led by @leonooi.bsky.social @csabaorban.bsky.social @shaoshiz.bsky.social
AI performance is known to scale with logarithm of sample size (Kaplan 2020), but in many domains, sample size can be # participants or # measurements...
doi.org/10.1038/s415...
AI performance is known to scale with logarithm of sample size (Kaplan 2020), but in many domains, sample size can be # participants or # measurements...
doi.org/10.1038/s415...
July 17, 2025 at 1:36 AM
1/11 Excited to share our @Naturestudy led by @leonooi.bsky.social @csabaorban.bsky.social @shaoshiz.bsky.social
AI performance is known to scale with logarithm of sample size (Kaplan 2020), but in many domains, sample size can be # participants or # measurements...
doi.org/10.1038/s415...
AI performance is known to scale with logarithm of sample size (Kaplan 2020), but in many domains, sample size can be # participants or # measurements...
doi.org/10.1038/s415...
Our Nature paper on the hashtag#scaling hashtag#behavior and economics of hashtag#machine hashtag#learning predictions in high-dimensional brain scans is out !
Congrats to the whole team.
www.nature.com/articles/s41...
Congrats to the whole team.
www.nature.com/articles/s41...
July 16, 2025 at 3:40 PM
Our Nature paper on the hashtag#scaling hashtag#behavior and economics of hashtag#machine hashtag#learning predictions in high-dimensional brain scans is out !
Congrats to the whole team.
www.nature.com/articles/s41...
Congrats to the whole team.
www.nature.com/articles/s41...
June 22, 2025 at 10:52 AM
I am impressed by this book I am currently reading: Kissinger's posthumous work on:
-strong anthropological views on the current AI evolution
-modes in which #AI could take space as a physical and intellectual actor
-how modes of decision making of humans and machines can coalesce and completment
-strong anthropological views on the current AI evolution
-modes in which #AI could take space as a physical and intellectual actor
-how modes of decision making of humans and machines can coalesce and completment
May 28, 2025 at 1:52 PM
I am impressed by this book I am currently reading: Kissinger's posthumous work on:
-strong anthropological views on the current AI evolution
-modes in which #AI could take space as a physical and intellectual actor
-how modes of decision making of humans and machines can coalesce and completment
-strong anthropological views on the current AI evolution
-modes in which #AI could take space as a physical and intellectual actor
-how modes of decision making of humans and machines can coalesce and completment
Great opportunity to get generous postdoc funding to work at a Canadian university
May 15, 2025 at 12:05 AM
Great opportunity to get generous postdoc funding to work at a Canadian university
Big congrats to our former postdoc Andrea @andrealuppi.bsky.social for earning the Brain Star Award for his work !
can-acn.org/brain-star-a...
can-acn.org/brain-star-a...
May 6, 2025 at 2:45 PM
Big congrats to our former postdoc Andrea @andrealuppi.bsky.social for earning the Brain Star Award for his work !
can-acn.org/brain-star-a...
can-acn.org/brain-star-a...
Reposted by danilobzdok
Using multi-modal data from the UK Biobank, Zhou et al. delineate the phenotyping and brain basis of early risers and night owls at a population scale, showing links to habit formation and emotional regulation.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Multimodal population study reveals the neurobiological underpinnings of chronotype - Nature Human Behaviour
Capitalizing on multimodel data from the UK Biobank, Bzdok and colleagues delineate the deep phenotyping and brain basis of early risers and night owls at a population scale, showing links to habit fo...
www.nature.com
April 17, 2025 at 8:17 PM
Using multi-modal data from the UK Biobank, Zhou et al. delineate the phenotyping and brain basis of early risers and night owls at a population scale, showing links to habit formation and emotional regulation.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Everything you always wanted to know about
how #night #owls and #early #risers are different.
Out today !
www.nature.com/articles/s41...
rdcu.be/eh8ix
@pessoabrain.bsky.social @ohbmofficial.bsky.social @sfn.org @nature.com @mcgilluniversity.bsky.social
how #night #owls and #early #risers are different.
Out today !
www.nature.com/articles/s41...
rdcu.be/eh8ix
@pessoabrain.bsky.social @ohbmofficial.bsky.social @sfn.org @nature.com @mcgilluniversity.bsky.social
Multimodal population study reveals the neurobiological underpinnings of chronotype - Nature Human Behaviour
Capitalizing on multimodel data from the UK Biobank, Bzdok and colleagues delineate the deep phenotyping and brain basis of early risers and night owls at a population scale, showing links to habit fo...
www.nature.com
April 17, 2025 at 1:49 PM
Everything you always wanted to know about
how #night #owls and #early #risers are different.
Out today !
www.nature.com/articles/s41...
rdcu.be/eh8ix
@pessoabrain.bsky.social @ohbmofficial.bsky.social @sfn.org @nature.com @mcgilluniversity.bsky.social
how #night #owls and #early #risers are different.
Out today !
www.nature.com/articles/s41...
rdcu.be/eh8ix
@pessoabrain.bsky.social @ohbmofficial.bsky.social @sfn.org @nature.com @mcgilluniversity.bsky.social
Just finished my slides for World AI Summit Headliner talk this week.
April 14, 2025 at 3:47 PM
Just finished my slides for World AI Summit Headliner talk this week.
Reposted by danilobzdok
FYI, if you want to be prepared to apply for the next ABCD Study data release, prepare for these new NIST security requirements 🧠: @ohbmofficial.bsky.social abcdstudy.org/scientists/d...
Data Sharing - ABCD Study
abcdstudy.org
March 31, 2025 at 5:53 PM
FYI, if you want to be prepared to apply for the next ABCD Study data release, prepare for these new NIST security requirements 🧠: @ohbmofficial.bsky.social abcdstudy.org/scientists/d...
Reposted by danilobzdok
#AUTISM “A data-driven revision of criteria ... grounded on clinical certainty, would complement what has historically been done by expert panels and ... humans, who can be wrong." @danilobzdok.bsky.social @mila-quebec.bsky.social @cellpress.bsky.social #AI
nouvelles.umontreal.ca/en/article/2...
nouvelles.umontreal.ca/en/article/2...
Using LLMs to understand how autism gets diagnosed
In a study that used large language models to analyze healthcare records of Quebec francophone children, scientists argue that current criteria for diagnosing autism are in need of revision.
nouvelles.umontreal.ca
March 26, 2025 at 8:23 PM
#AUTISM “A data-driven revision of criteria ... grounded on clinical certainty, would complement what has historically been done by expert panels and ... humans, who can be wrong." @danilobzdok.bsky.social @mila-quebec.bsky.social @cellpress.bsky.social #AI
nouvelles.umontreal.ca/en/article/2...
nouvelles.umontreal.ca/en/article/2...
Jack Stanley shows how to tailor #LLMs for single-sentence prediction in #autism:
www.cell.com/cell/fulltex...
Great collabo with Eugene Belilovsky + Siva Reddy from @mila-quebec.bsky.social, and Laurent Mottron + Emmett Rabot
www.cell.com/cell/fulltex...
Great collabo with Eugene Belilovsky + Siva Reddy from @mila-quebec.bsky.social, and Laurent Mottron + Emmett Rabot
March 26, 2025 at 5:29 PM
Jack Stanley shows how to tailor #LLMs for single-sentence prediction in #autism:
www.cell.com/cell/fulltex...
Great collabo with Eugene Belilovsky + Siva Reddy from @mila-quebec.bsky.social, and Laurent Mottron + Emmett Rabot
www.cell.com/cell/fulltex...
Great collabo with Eugene Belilovsky + Siva Reddy from @mila-quebec.bsky.social, and Laurent Mottron + Emmett Rabot
Reposted by danilobzdok
Trained language model finds repetitive behaviors and special interests are more indicative of an autism diagnosis than a lack of social skills. https://www.cell.com/cell/fulltext/S0092-8674(25)00213-2
@mila-quebec.bsky.social @Danilo Bzdo
@mila-quebec.bsky.social @Danilo Bzdo
March 26, 2025 at 3:00 PM
Trained language model finds repetitive behaviors and special interests are more indicative of an autism diagnosis than a lack of social skills. https://www.cell.com/cell/fulltext/S0092-8674(25)00213-2
@mila-quebec.bsky.social @Danilo Bzdo
@mila-quebec.bsky.social @Danilo Bzdo
Reposted by danilobzdok
Mila researchers Jack Stanley and Danilo Bzdok published a paper in the journal @cellpress.bsky.social. Their work uses LLMs to analyse data from written reports by medical professionals in order to better understand and improve how autism diagnosis is performed. mila.quebec/en/article/u...
March 26, 2025 at 3:30 PM
Mila researchers Jack Stanley and Danilo Bzdok published a paper in the journal @cellpress.bsky.social. Their work uses LLMs to analyse data from written reports by medical professionals in order to better understand and improve how autism diagnosis is performed. mila.quebec/en/article/u...
Reposted by danilobzdok
Understanding #Parkinsons subtypes is key to more targeted RCTs & better therapeutics! 🧠 Our new study finds that LRRK2 PD patients show milder cortical atrophy, with preserved temporal & occipital regions compared to sporadic PD. #LRRK2 #dataviz
www.medrxiv.org/content/10.1...
www.medrxiv.org/content/10.1...
March 12, 2025 at 1:57 PM
Understanding #Parkinsons subtypes is key to more targeted RCTs & better therapeutics! 🧠 Our new study finds that LRRK2 PD patients show milder cortical atrophy, with preserved temporal & occipital regions compared to sporadic PD. #LRRK2 #dataviz
www.medrxiv.org/content/10.1...
www.medrxiv.org/content/10.1...
🔥🔥🔥
Understanding #Parkinsons subtypes is key to more targeted RCTs & better therapeutics! 🧠 Our new study finds that LRRK2 PD patients show milder cortical atrophy, with preserved temporal & occipital regions compared to sporadic PD. #LRRK2 #dataviz
www.medrxiv.org/content/10.1...
www.medrxiv.org/content/10.1...
March 12, 2025 at 1:58 PM
🔥🔥🔥
@oprah-winfrey.bsky.social and @michaelpollan.bsky.social make unmistakably clear: there is widespread interest in #psychedelics
>1M views in less than a week, bravo !
>1M views in less than a week, bravo !
March 10, 2025 at 11:21 PM
@oprah-winfrey.bsky.social and @michaelpollan.bsky.social make unmistakably clear: there is widespread interest in #psychedelics
>1M views in less than a week, bravo !
>1M views in less than a week, bravo !
Reposted by danilobzdok
My talk on “Neuroscience and AI: a symbiosis” @SimonsInstitute
I start with a whirlwind history of metaphors for intelligence, spanning Hippocratic hydraulics, Hobbesian clocks, Cartesian dualism to Turing, telegraphs, Hopfield, and deep learning. simons.berkeley.edu/talks/surya-...
I start with a whirlwind history of metaphors for intelligence, spanning Hippocratic hydraulics, Hobbesian clocks, Cartesian dualism to Turing, telegraphs, Hopfield, and deep learning. simons.berkeley.edu/talks/surya-...
March 7, 2025 at 3:57 PM
My talk on “Neuroscience and AI: a symbiosis” @SimonsInstitute
I start with a whirlwind history of metaphors for intelligence, spanning Hippocratic hydraulics, Hobbesian clocks, Cartesian dualism to Turing, telegraphs, Hopfield, and deep learning. simons.berkeley.edu/talks/surya-...
I start with a whirlwind history of metaphors for intelligence, spanning Hippocratic hydraulics, Hobbesian clocks, Cartesian dualism to Turing, telegraphs, Hopfield, and deep learning. simons.berkeley.edu/talks/surya-...
March 6, 2025 at 8:55 PM
@evfedorenko.bsky.social at Berkley LLM workshop gave insightful talk today:
-Broca / Wernicke s are speech areas, not language areas per se
-language networks similar across 50 languages
-most language voxel are INsensitive to semantics
-lesion studies suggest thought intact but speech impaired
-Broca / Wernicke s are speech areas, not language areas per se
-language networks similar across 50 languages
-most language voxel are INsensitive to semantics
-lesion studies suggest thought intact but speech impaired
February 6, 2025 at 7:30 PM
@evfedorenko.bsky.social at Berkley LLM workshop gave insightful talk today:
-Broca / Wernicke s are speech areas, not language areas per se
-language networks similar across 50 languages
-most language voxel are INsensitive to semantics
-lesion studies suggest thought intact but speech impaired
-Broca / Wernicke s are speech areas, not language areas per se
-language networks similar across 50 languages
-most language voxel are INsensitive to semantics
-lesion studies suggest thought intact but speech impaired
@suryaganguli.bsky.social gives great talk at LLM workshop at Berkley
-LLM<->brain is still a new topic, less progress so far than LLM<->vision
-lets train LLM foundation models of specific brain systems and then reverse engineer them
-emerging paradigm: read-write experiments in brains+machines
-LLM<->brain is still a new topic, less progress so far than LLM<->vision
-lets train LLM foundation models of specific brain systems and then reverse engineer them
-emerging paradigm: read-write experiments in brains+machines
February 3, 2025 at 7:49 PM
@suryaganguli.bsky.social gives great talk at LLM workshop at Berkley
-LLM<->brain is still a new topic, less progress so far than LLM<->vision
-lets train LLM foundation models of specific brain systems and then reverse engineer them
-emerging paradigm: read-write experiments in brains+machines
-LLM<->brain is still a new topic, less progress so far than LLM<->vision
-lets train LLM foundation models of specific brain systems and then reverse engineer them
-emerging paradigm: read-write experiments in brains+machines
Now accepted at Nature Computational Science:
Nicole shows how #Bayesian #hierarchical #models can explicitly model major #source of #population #stratification in 10,000 ABCD subjects.
pmc.ncbi.nlm.nih.gov/articles/PMC...
Nicole shows how #Bayesian #hierarchical #models can explicitly model major #source of #population #stratification in 10,000 ABCD subjects.
pmc.ncbi.nlm.nih.gov/articles/PMC...
January 28, 2025 at 7:15 PM
Now accepted at Nature Computational Science:
Nicole shows how #Bayesian #hierarchical #models can explicitly model major #source of #population #stratification in 10,000 ABCD subjects.
pmc.ncbi.nlm.nih.gov/articles/PMC...
Nicole shows how #Bayesian #hierarchical #models can explicitly model major #source of #population #stratification in 10,000 ABCD subjects.
pmc.ncbi.nlm.nih.gov/articles/PMC...
Will be in San Francisco beginning february for the @IVADO_Qc workshop on large language models and #transformers at Berkley’s
Simons Institute for the Theory of Computing.
simons.berkeley.edu/programs/spe...
Please DM if you want to chat.
Simons Institute for the Theory of Computing.
simons.berkeley.edu/programs/spe...
Please DM if you want to chat.
Special Year on Large Language Models and Transformers, Part 2
This is the second part in a special year-long program on large language models and transformers that spans the 2024–2025 academic year. This program's overarching goal is to try to understand the ong...
simons.berkeley.edu
January 23, 2025 at 11:23 AM
Will be in San Francisco beginning february for the @IVADO_Qc workshop on large language models and #transformers at Berkley’s
Simons Institute for the Theory of Computing.
simons.berkeley.edu/programs/spe...
Please DM if you want to chat.
Simons Institute for the Theory of Computing.
simons.berkeley.edu/programs/spe...
Please DM if you want to chat.