Raymond Chua
@raymondrchua.bsky.social
NeuroAI PhD Candidate at McGill / Mila.
Loves: 🧠 🏕️ 🏔️ 🏊🏻♂️ 🚴🏻♂️ 🏃🏻♂️ 🎨📚☕
https://raymondchua.github.io
Loves: 🧠 🏕️ 🏔️ 🏊🏻♂️ 🚴🏻♂️ 🏃🏻♂️ 🎨📚☕
https://raymondchua.github.io
Pinned
Learning Successor Features the Simple Way
In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) off...
arxiv.org
It’s been a long time coming, but I’m thrilled to share my first research paper with @arnaghosh.bsky.social , Christos, @tyrellturing.bsky.social , and Doina! Just accepted to NeurIPS 2024 (Vancouver! 🇨🇦). This will be a longer thread—thanks for following along! arxiv.org/abs/2410.22133
1/11
1/11
Reposted by Raymond Chua
My Canadian university, Queen's, is offering TWENTY 4-year funded PhDs (40k CAD/yr) for a student of ANY citizenship who has been accepted at a top 100 US university but have had offer rescinded OR are reconsidering offer due to US policy.
Details found here👇
www.queensu.ca/grad-postdoc...
Details found here👇
www.queensu.ca/grad-postdoc...
Queen’s Special U.S. Doctoral Recruitment Initiative | School of Graduate Studies and Postdoctoral AffairsDown arrowDown arrowDown arrowDown arrowDown arrowDown arrowDown arrowDown arrowDown arrowDown...
Queen’s University is a globally engaged, research-intensive institution dedicated to attracting and supporting exceptional PhD students who will significantly advance our research mission.
www.queensu.ca
June 5, 2025 at 3:31 PM
My Canadian university, Queen's, is offering TWENTY 4-year funded PhDs (40k CAD/yr) for a student of ANY citizenship who has been accepted at a top 100 US university but have had offer rescinded OR are reconsidering offer due to US policy.
Details found here👇
www.queensu.ca/grad-postdoc...
Details found here👇
www.queensu.ca/grad-postdoc...
Couldn't agree more. Rather than burying the experiments that did not work, we should embrace them and consider the results in their entirety.
Going to the hospital because I broke my wrist smashing the endorse button:
www.understandingai.org/p/i-got-fool...
www.understandingai.org/p/i-got-fool...
I got fooled by AI-for-science hype—here's what it taught me
I used AI in my plasma physics research and it didn’t go the way I expected.
www.understandingai.org
May 19, 2025 at 10:35 PM
Couldn't agree more. Rather than burying the experiments that did not work, we should embrace them and consider the results in their entirety.
Reposted by Raymond Chua
My lab is hosting undergraduates for the SURFiN program. If you want to come to @yorku-neurophys.bsky.social @yorku-cian.bsky.social in Toronto and work on a @simonsfoundation.org funded project on using brain-inspired AI for autism research please apply!
www.simonsfoundation.org/grant/shenoy...
www.simonsfoundation.org/grant/shenoy...
Shenoy Undergraduate Research Fellowship in Neuroscience (SURFiN)
Shenoy Undergraduate Research Fellowship in Neuroscience (SURFiN) on Simons Foundation
www.simonsfoundation.org
April 17, 2025 at 1:20 AM
My lab is hosting undergraduates for the SURFiN program. If you want to come to @yorku-neurophys.bsky.social @yorku-cian.bsky.social in Toronto and work on a @simonsfoundation.org funded project on using brain-inspired AI for autism research please apply!
www.simonsfoundation.org/grant/shenoy...
www.simonsfoundation.org/grant/shenoy...
Reposted by Raymond Chua
How does our brain predict the future? Our review of predictive processing + research program is now on arXiv arxiv.org/abs/2504.09614
50+ neuroscientists distributed across the world worked together to create this unique community project.
50+ neuroscientists distributed across the world worked together to create this unique community project.
April 15, 2025 at 6:58 AM
How does our brain predict the future? Our review of predictive processing + research program is now on arXiv arxiv.org/abs/2504.09614
50+ neuroscientists distributed across the world worked together to create this unique community project.
50+ neuroscientists distributed across the world worked together to create this unique community project.
Excited to my favourite conference will be back in Montreal this week! Looking forward to catching up with old friends as well as making new ones! If you are attending the main conference or the workshops and would love to chat, let me know! :)
Attending @cosynemeeting.bsky.social? Check out @tonyzador.bsky.social’s account of what motivated him to launch the meeting 30-plus years ago, and why cross-disciplinary conferences are so important.
#neuroskyence
www.thetransmitter.org/computationa...
#neuroskyence
www.thetransmitter.org/computationa...
The origins of COSYNE: Building a community
Thirty years ago, theoretical and experimental neuroscientists rarely went to the same conferences. So I helped launch a meeting to get them talking.
www.thetransmitter.org
March 24, 2025 at 9:31 PM
Excited to my favourite conference will be back in Montreal this week! Looking forward to catching up with old friends as well as making new ones! If you are attending the main conference or the workshops and would love to chat, let me know! :)
Reposted by Raymond Chua
Join us at this #COSYNE2025 workshop to discuss foundation models for neuroscience!!!
#neuroscience #NeuroAI #MLSky 🧪
#neuroscience #NeuroAI #MLSky 🧪
How can large-scale models + datasets revolutionize neuroscience 🧠🤖🌐? We are excited to announce our workshop: “Building a foundation model for the brain: datasets, theory, and models” at @cosynemeeting.bsky.social #COSYNE2025. Join us in Mont-Tremblant, Canada from March 31 – April 1!
March 10, 2025 at 7:56 PM
Join us at this #COSYNE2025 workshop to discuss foundation models for neuroscience!!!
#neuroscience #NeuroAI #MLSky 🧪
#neuroscience #NeuroAI #MLSky 🧪
As always, I enjoy learning and hearing the wise words from Prof. Rich Sutton, the new Turing Award winner! As he put it, there are no authorities in Science and anyone can question anyone else. www.youtube.com/watch?v=9_Pe...
TURING AWARD WINNER Richard S. Sutton in Conversation with Cam Linke | No Authorities in Science
YouTube video by Amii
www.youtube.com
March 5, 2025 at 7:43 PM
As always, I enjoy learning and hearing the wise words from Prof. Rich Sutton, the new Turing Award winner! As he put it, there are no authorities in Science and anyone can question anyone else. www.youtube.com/watch?v=9_Pe...
Reposted by Raymond Chua
Very well deserved! Congrats to Andy & Rich!
#ReinforcementLearning (Barto&Sutton) wins the Turing! Wonderful recognition for two personal heroes of mine as well as for the whole field!
www.nytimes.com/2025/03/05/t...
www.nytimes.com/2025/03/05/t...
Turing Award Goes to A.I. Pioneers Andrew Barto and Richard Sutton
Andrew Barto and Richard Sutton developed reinforcement learning, a technique vital to chatbots like ChatGPT.
www.nytimes.com
March 5, 2025 at 12:04 PM
Very well deserved! Congrats to Andy & Rich!
Reposted by Raymond Chua
Who is a cognitive scientist? There's been fascinating discussion about cognition, but I'm as interested in who we think of as cognitive scientists. New essay includes a visual presentation of cog-sci's historical diversity--or lack thereof. buildcognitiveresonance.substack.com/p/who-is-a-c...
Who is a cognitive scientist?
It depends on how you look
buildcognitiveresonance.substack.com
February 19, 2025 at 6:04 PM
Who is a cognitive scientist? There's been fascinating discussion about cognition, but I'm as interested in who we think of as cognitive scientists. New essay includes a visual presentation of cog-sci's historical diversity--or lack thereof. buildcognitiveresonance.substack.com/p/who-is-a-c...
Looking forward to this new NeuroAI symposium! 🧠
The call for abstracts and registration links are now open for our virtual & in-person symposium in June! Learn more: bit.ly/41wSYJA #KempnerInstitute #NeuroAI
January 31, 2025 at 3:56 PM
Looking forward to this new NeuroAI symposium! 🧠
Thrilled to see this paper finally published! The manifold representations in Figure 1H were a key inspiration behind the visualization of Successor Features (SF) in our recent SF paper. It's fascinating how insights from neuroscience can help us interpret representations learned in deep RL.
January 28, 2025 at 5:48 PM
Thrilled to see this paper finally published! The manifold representations in Figure 1H were a key inspiration behind the visualization of Successor Features (SF) in our recent SF paper. It's fascinating how insights from neuroscience can help us interpret representations learned in deep RL.
Lately, foundation models like BrainGPT & Cognitive FMs are dominating AI & science. But is our future solely built on these models? What about alternative techniques? How do we keep our scientific ecosystem diverse? As a community, where do we see the future of NeuroAI?
January 13, 2025 at 12:02 AM
Lately, foundation models like BrainGPT & Cognitive FMs are dominating AI & science. But is our future solely built on these models? What about alternative techniques? How do we keep our scientific ecosystem diverse? As a community, where do we see the future of NeuroAI?
Reposted by Raymond Chua
This is FASCINATING! Thanks for sharing @kmpanthagani.bsky.social www.youcanknowthings.com/how-one-neur...
How a neuroscientist solved the mystery of his own long COVID
When Jeff Yau started having strange symptoms after his COVID-19 infection – numbness, tingling, and shaking – he experienced what thousands of others with long COVID have found: answers were hard to ...
www.youcanknowthings.com
January 9, 2025 at 2:01 AM
This is FASCINATING! Thanks for sharing @kmpanthagani.bsky.social www.youcanknowthings.com/how-one-neur...
Reposted by Raymond Chua
Key-value memory is an important concept in modern machine learning (e.g., transformers). Ila Fiete, Kazuki Irie, and I have written a paper showing how key-value memory provides a way of thinking about memory organization in the brain:
arxiv.org/abs/2501.02950
arxiv.org/abs/2501.02950
Key-value memory in the brain
Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored patterns. While parsimo...
arxiv.org
January 7, 2025 at 9:21 AM
Key-value memory is an important concept in modern machine learning (e.g., transformers). Ila Fiete, Kazuki Irie, and I have written a paper showing how key-value memory provides a way of thinking about memory organization in the brain:
arxiv.org/abs/2501.02950
arxiv.org/abs/2501.02950
Reposted by Raymond Chua
Please, spread!
🧠 Competitive PhD funding is available for neuroscience projects in the Parisian region. Consider your options 👇
dim-cbrains.fr/en/phd-progr...
@c-brains.bsky.social
🧠 Competitive PhD funding is available for neuroscience projects in the Parisian region. Consider your options 👇
dim-cbrains.fr/en/phd-progr...
@c-brains.bsky.social
DIM C-BRAINS
Cognition and Brain Revolutions: Artificial Intelligence, Neurogenomics, Society
dim-cbrains.fr
January 6, 2025 at 12:59 PM
Please, spread!
🧠 Competitive PhD funding is available for neuroscience projects in the Parisian region. Consider your options 👇
dim-cbrains.fr/en/phd-progr...
@c-brains.bsky.social
🧠 Competitive PhD funding is available for neuroscience projects in the Parisian region. Consider your options 👇
dim-cbrains.fr/en/phd-progr...
@c-brains.bsky.social
Reposted by Raymond Chua
Cutting it a bit fine, but here’s my review of the year in neuroscience for 2024
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
2024: A Review of the Year in Neuroscience
Feeling a bit wired
medium.com
December 30, 2024 at 4:00 PM
Cutting it a bit fine, but here’s my review of the year in neuroscience for 2024
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
The eighth of these, would you believe? We’ve got dark neurons, tiny monkeys, the most complete brain wiring diagram ever constructed, and much more…
Published on The Spike
Enjoy!
medium.com/the-spike/20...
Something to think about if you are pursuing Non-LLM fundamental research during your PhD.
Doing research for scientific advancement in industry, instead of for product improvement, was something many of us took for granted for years.
There are very few places where that's still possible (GDM is one), and much harder to get hired for a position like this nowadays.
There are very few places where that's still possible (GDM is one), and much harder to get hired for a position like this nowadays.
December 20, 2024 at 9:01 PM
Something to think about if you are pursuing Non-LLM fundamental research during your PhD.
Reposted by Raymond Chua
Why does anyone have any issue with this?
I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on.
But, I literally don't see why this is problematic...
I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on.
But, I literally don't see why this is problematic...
This would be funny if it weren't sad...
Coming from the "giants" of AI.
Or maybe this was posted out of context? Please clarify.
I can't process this...
Coming from the "giants" of AI.
Or maybe this was posted out of context? Please clarify.
I can't process this...
December 16, 2024 at 5:27 PM
Why does anyone have any issue with this?
I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on.
But, I literally don't see why this is problematic...
I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on.
But, I literally don't see why this is problematic...
Reposted by Raymond Chua
I've been arguing that we will be able to train foundation models on neural data from different species, because I suspect that there are sufficiently preserved motifs in neural computation across the phylgenetic tree.
This paper appears to support that idea!
www.cell.com/cell/abstrac...
🧠📈 🧪
This paper appears to support that idea!
www.cell.com/cell/abstrac...
🧠📈 🧪
Multiscale organization of neuronal activity unifies scale-dependent theories of brain function
Analysis of cellular recordings from five phylogenetically diverse species uncovers a conserved, multiscale organization of neuronal activity that resolves disparate theories of brain function. This hierarchical structure allows the brain to operate across multiple timescales, enhances information flow, flexibly reconfigures activity during behavior, and balances functional resiliency with efficiency across scales.
www.cell.com
December 12, 2024 at 5:04 PM
I've been arguing that we will be able to train foundation models on neural data from different species, because I suspect that there are sufficiently preserved motifs in neural computation across the phylgenetic tree.
This paper appears to support that idea!
www.cell.com/cell/abstrac...
🧠📈 🧪
This paper appears to support that idea!
www.cell.com/cell/abstrac...
🧠📈 🧪
Reposted by Raymond Chua
NEW: we have an exciting opportunity for a tenure-track professor at the #KempnerInstitute and the John A. Paulson School of Engineering and Applied Sciences (SEAS). Read the full description & apply today: academicpositions.harvard.edu/postings/14362
#ML #AI
#ML #AI
December 3, 2024 at 1:24 AM
NEW: we have an exciting opportunity for a tenure-track professor at the #KempnerInstitute and the John A. Paulson School of Engineering and Applied Sciences (SEAS). Read the full description & apply today: academicpositions.harvard.edu/postings/14362
#ML #AI
#ML #AI
Reposted by Raymond Chua
Happy to have contributed to the `Brain Prize` webminar Series on LLMs and the Human Brain:
www.youtube.com/watch?v=UyJx...
Here is the full set of seminars:
lundbeckfonden.com/brain-prize-...
(And congrats again to Larry Abbott, Terry Sejnowski and Haim Sompolinsky!)
www.youtube.com/watch?v=UyJx...
Here is the full set of seminars:
lundbeckfonden.com/brain-prize-...
(And congrats again to Larry Abbott, Terry Sejnowski and Haim Sompolinsky!)
Webinar 6: LLMs and Human Language Processing
YouTube video by BrainPrize
www.youtube.com
December 3, 2024 at 9:45 AM
Happy to have contributed to the `Brain Prize` webminar Series on LLMs and the Human Brain:
www.youtube.com/watch?v=UyJx...
Here is the full set of seminars:
lundbeckfonden.com/brain-prize-...
(And congrats again to Larry Abbott, Terry Sejnowski and Haim Sompolinsky!)
www.youtube.com/watch?v=UyJx...
Here is the full set of seminars:
lundbeckfonden.com/brain-prize-...
(And congrats again to Larry Abbott, Terry Sejnowski and Haim Sompolinsky!)
Hey Bluesky friends! I will be spending a few days in San Francisco before NeurIPS and would love to connect with others who share similar research interests! Whether it’s over coffee or a run, I’m happy to chat about NeuroAI, RL, or anything in between. Let me know if you’re around! 🙂
December 3, 2024 at 2:19 AM
Hey Bluesky friends! I will be spending a few days in San Francisco before NeurIPS and would love to connect with others who share similar research interests! Whether it’s over coffee or a run, I’m happy to chat about NeuroAI, RL, or anything in between. Let me know if you’re around! 🙂
Reposted by Raymond Chua
Go work with Jonny!
Delighted to be in Leeds joining the School of Computing! Fantastic first impressions — like a "less offensive London" (youtu.be/watch?v=_6_VVLgrgFI). Stay tuned for a PhD position starting next October. Meanwhile, drop me a message with your CV and research interests—I'd love to hear from you!
Pleased to welcome @repromancer.bsky.social - a computational neuroscientist - to the @universityofleeds.bsky.social today - working on the boundary of neuroscience and AI. Welcome Jonathan!
November 29, 2024 at 4:28 PM
Go work with Jonny!
Reposted by Raymond Chua
𝗪𝗵𝗮𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗯𝗿𝗮𝗶𝗻 𝗶𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁𝘀 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗰𝗼𝗺𝗽𝘂𝘁𝗮𝘁𝗶𝗼𝗻?
Maybe not neurons, perhaps RNA??
Great episode of Brain Inspired with Hessam Akhlaghpour.
Do dynamical systems and/or RNNs implement universal computation? This discussion alone would be worth having.
#neuroscience
braininspired.co/podcast/199/
Maybe not neurons, perhaps RNA??
Great episode of Brain Inspired with Hessam Akhlaghpour.
Do dynamical systems and/or RNNs implement universal computation? This discussion alone would be worth having.
#neuroscience
braininspired.co/podcast/199/
BI 199 Hessam Akhlaghpour: Natural Universal Computation | Brain Inspired
braininspired.co
November 27, 2024 at 6:27 PM
𝗪𝗵𝗮𝘁 𝗶𝗻 𝘁𝗵𝗲 𝗯𝗿𝗮𝗶𝗻 𝗶𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁𝘀 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗰𝗼𝗺𝗽𝘂𝘁𝗮𝘁𝗶𝗼𝗻?
Maybe not neurons, perhaps RNA??
Great episode of Brain Inspired with Hessam Akhlaghpour.
Do dynamical systems and/or RNNs implement universal computation? This discussion alone would be worth having.
#neuroscience
braininspired.co/podcast/199/
Maybe not neurons, perhaps RNA??
Great episode of Brain Inspired with Hessam Akhlaghpour.
Do dynamical systems and/or RNNs implement universal computation? This discussion alone would be worth having.
#neuroscience
braininspired.co/podcast/199/