Zhipeng Huang
@nopainkiller.bsky.social
Open Source Accelerates Everything
Reposted by Zhipeng Huang
Imagine a brain decoding algorithm that could generalize across different subjects and tasks. Today, we’re one step closer to achieving that vision.
Introducing the flagship paper of our brain decoding program: www.biorxiv.org/content/10.1...
#neuroAI #compneuro @utoronto.ca @uhn.ca
Introducing the flagship paper of our brain decoding program: www.biorxiv.org/content/10.1...
#neuroAI #compneuro @utoronto.ca @uhn.ca
October 7, 2025 at 12:53 PM
Imagine a brain decoding algorithm that could generalize across different subjects and tasks. Today, we’re one step closer to achieving that vision.
Introducing the flagship paper of our brain decoding program: www.biorxiv.org/content/10.1...
#neuroAI #compneuro @utoronto.ca @uhn.ca
Introducing the flagship paper of our brain decoding program: www.biorxiv.org/content/10.1...
#neuroAI #compneuro @utoronto.ca @uhn.ca
Big congrats ！
1/4) I’m excited to announce that I have joined the Paradigms of Intelligence team at Google (github.com/paradigms-of...)! Our team, led by @blaiseaguera.bsky.social, is bringing forward the next stage of AI by pushing on some of the assumptions that underpin current ML.
#MLSky #AI #neuroscience
#MLSky #AI #neuroscience
Paradigms of Intelligence Team
Advance our understanding of how intelligence evolves to develop new technologies for the benefit of humanity and other sentient life - Paradigms of Intelligence Team
github.com
September 24, 2025 at 1:49 AM
Big congrats ！
Reposted by Zhipeng Huang
Very happy to see that Pleias multilingual data processing pipelines have contributed to the largest open pretraining project in Europe.
From their tech report: huggingface.co/swiss-ai/Ape...
From their tech report: huggingface.co/swiss-ai/Ape...
September 2, 2025 at 4:46 PM
Very happy to see that Pleias multilingual data processing pipelines have contributed to the largest open pretraining project in Europe.
From their tech report: huggingface.co/swiss-ai/Ape...
From their tech report: huggingface.co/swiss-ai/Ape...
Reposted by Zhipeng Huang
Not that it comes as much of a surprise to many of us, but it's worth emphasizing once again - the 👏 brain 👏 uses 👏 distributed 👏 coding 👏. 😁
Two new papers from the #IBL looking at brain-wide activity:
www.nature.com/articles/s41...
www.nature.com/articles/s41...
#neuroscience 🧪
Two new papers from the #IBL looking at brain-wide activity:
www.nature.com/articles/s41...
www.nature.com/articles/s41...
#neuroscience 🧪
Brain-wide representations of prior information in mouse decision-making - Nature
Brain-wide recordings in mice reveal that prior expectations are distributed through recurrent loops across all levels of cortical and subcortical processing.
www.nature.com
September 4, 2025 at 2:40 PM
Not that it comes as much of a surprise to many of us, but it's worth emphasizing once again - the 👏 brain 👏 uses 👏 distributed 👏 coding 👏. 😁
Two new papers from the #IBL looking at brain-wide activity:
www.nature.com/articles/s41...
www.nature.com/articles/s41...
#neuroscience 🧪
Two new papers from the #IBL looking at brain-wide activity:
www.nature.com/articles/s41...
www.nature.com/articles/s41...
#neuroscience 🧪
Reposted by Zhipeng Huang
Stunning cryo-ET from Peijun Zhang lab: Direct visualization of HIV-1 nuclear import!
Hundreds of viral cores captured entering the nucleus. The NPC dilates to let the capsid through. A masterclass in correlative microscopy that makes it quantitative. A leap for structural virology! @emboreports.org
Hundreds of viral cores captured entering the nucleus. The NPC dilates to let the capsid through. A masterclass in correlative microscopy that makes it quantitative. A leap for structural virology! @emboreports.org
August 29, 2025 at 1:42 PM
Stunning cryo-ET from Peijun Zhang lab: Direct visualization of HIV-1 nuclear import!
Hundreds of viral cores captured entering the nucleus. The NPC dilates to let the capsid through. A masterclass in correlative microscopy that makes it quantitative. A leap for structural virology! @emboreports.org
Hundreds of viral cores captured entering the nucleus. The NPC dilates to let the capsid through. A masterclass in correlative microscopy that makes it quantitative. A leap for structural virology! @emboreports.org
Reposted by Zhipeng Huang
Internship Position on the Lattice Estimator martinralbrecht.wordpress.com/2025/08/27/i...
Internship Position on the Lattice Estimator
Eamonn and I are looking to hire an intern for four months to work on the Lattice Estimator. The internship will be based at King’s College London and is funded by a gift from Zama. We are ideally …
martinralbrecht.wordpress.com
August 27, 2025 at 1:50 PM
Internship Position on the Lattice Estimator martinralbrecht.wordpress.com/2025/08/27/i...
Reposted by Zhipeng Huang
In short, world-class research from NeurIPS accessible in Europe.
EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego.
Follow this account for more updates, and see you in wonderful Copenhagen 📅
eurips.cc
EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego.
Follow this account for more updates, and see you in wonderful Copenhagen 📅
eurips.cc
EurIPS Copenhagen 2025 - A NeurIPS-endorsed conference in Europe
A NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark
eurips.cc
August 27, 2025 at 6:41 AM
In short, world-class research from NeurIPS accessible in Europe.
EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego.
Follow this account for more updates, and see you in wonderful Copenhagen 📅
eurips.cc
EurIPS takes place over 3 days + 2 workshop days, at the same time as NeurIPS in San Diego.
Follow this account for more updates, and see you in wonderful Copenhagen 📅
eurips.cc
Reposted by Zhipeng Huang
Emmanuel Levy @elevylab.bsky.social has joined BlueSky 🌟 with a fantastic Cell paper with Shu-ou Shan, showing the interactome of the TOM complex and how cotranslational mito import prioritizes large globular domains. Beautiful science!
Give him a warm welcome 🎉
link: www.cell.com/cell/fulltex...
Give him a warm welcome 🎉
link: www.cell.com/cell/fulltex...
Principles of cotranslational mitochondrial protein import
Selective ribosome profiling reveals that nearly 20% of mitochondrial proteins in
human cells are imported during translation on cytosolic ribosomes. Cotranslational
import requires an N-terminal pres...
www.cell.com
August 22, 2025 at 3:00 AM
Emmanuel Levy @elevylab.bsky.social has joined BlueSky 🌟 with a fantastic Cell paper with Shu-ou Shan, showing the interactome of the TOM complex and how cotranslational mito import prioritizes large globular domains. Beautiful science!
Give him a warm welcome 🎉
link: www.cell.com/cell/fulltex...
Give him a warm welcome 🎉
link: www.cell.com/cell/fulltex...
Reposted by Zhipeng Huang
EurIPS includes a call for both Workshops and Affinity Workshops!
We look forward to making #EurIPS a diverse and inclusive event with you.
The submission deadlines are August 22nd, AoE.
More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...
We look forward to making #EurIPS a diverse and inclusive event with you.
The submission deadlines are August 22nd, AoE.
More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...
July 28, 2025 at 8:51 AM
EurIPS includes a call for both Workshops and Affinity Workshops!
We look forward to making #EurIPS a diverse and inclusive event with you.
The submission deadlines are August 22nd, AoE.
More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...
We look forward to making #EurIPS a diverse and inclusive event with you.
The submission deadlines are August 22nd, AoE.
More information at:
eurips.cc/call-for-wor...
eurips.cc/call-for-aff...
Reposted by Zhipeng Huang
Excited to be at ACL! Join us at the Table Representation Learning workshop tomorrow in room 2.15 to talk about tables and AI.
We also present a paper showing the sensitivity of LLMs in tabular reasoning to e.g. missing vals and duplicates, by @cowolff.bsky.social at 16:50: arxiv.org/abs/2505.07453
We also present a paper showing the sensitivity of LLMs in tabular reasoning to e.g. missing vals and duplicates, by @cowolff.bsky.social at 16:50: arxiv.org/abs/2505.07453
July 30, 2025 at 10:24 PM
Excited to be at ACL! Join us at the Table Representation Learning workshop tomorrow in room 2.15 to talk about tables and AI.
We also present a paper showing the sensitivity of LLMs in tabular reasoning to e.g. missing vals and duplicates, by @cowolff.bsky.social at 16:50: arxiv.org/abs/2505.07453
We also present a paper showing the sensitivity of LLMs in tabular reasoning to e.g. missing vals and duplicates, by @cowolff.bsky.social at 16:50: arxiv.org/abs/2505.07453
Reposted by Zhipeng Huang
Reposted by Zhipeng Huang
In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:
![What do representations tell us about a system? Image of a mouse with a scope showing a vector of activity patterns, and a neural network with a vector of unit activity patterns
Common analyses of neural representations: Encoding models (relating activity to task features) drawing of an arrow from a trace saying [on_____on____] to a neuron and spike train. Comparing models via neural predictivity: comparing two neural networks by their R^2 to mouse brain activity. RSA: assessing brain-brain or model-brain correspondence using representational dissimilarity matrices](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:e6ewzleebkdi2y2bxhjxoknt/bafkreiav2io2ska33o4kizf57co5bboqyyfdpnozo2gxsicrfr5l7qzjcq@jpeg)
August 5, 2025 at 2:36 PM
In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:
Reposted by Zhipeng Huang
It was great to work on the ODAC25 paper with the Meta FAIR Chemistry and Georgia Tech. A leap forwards in modelling direct air carbon capture with metal organic frameworks, with much better data and larger models.
Paper: arxiv.org/abs/2508.03162
Data and models: huggingface.co/facebook/ODA...
Paper: arxiv.org/abs/2508.03162
Data and models: huggingface.co/facebook/ODA...
The Open DAC 2025 Dataset for Sorbent Discovery in Direct Air Capture
Identifying useful sorbent materials for direct air capture (DAC) from humid air remains a challenge. We present the Open DAC 2025 (ODAC25) dataset, a significant expansion and improvement upon ODAC23...
arxiv.org
August 7, 2025 at 11:25 PM
It was great to work on the ODAC25 paper with the Meta FAIR Chemistry and Georgia Tech. A leap forwards in modelling direct air carbon capture with metal organic frameworks, with much better data and larger models.
Paper: arxiv.org/abs/2508.03162
Data and models: huggingface.co/facebook/ODA...
Paper: arxiv.org/abs/2508.03162
Data and models: huggingface.co/facebook/ODA...
Reposted by Zhipeng Huang
1/ Excited to share a new preprint!
Our latest study uncovers how serotonin precisely controls the “time window” for fear learning, ensuring that our brains link cues (CS) & threats (US) only when it’s adaptive.
#Neuroscience #FearLearning
www.biorxiv.org/content/10.1...
Our latest study uncovers how serotonin precisely controls the “time window” for fear learning, ensuring that our brains link cues (CS) & threats (US) only when it’s adaptive.
#Neuroscience #FearLearning
www.biorxiv.org/content/10.1...
Serotonin shapes the temporal window for associative fear learning
Fear learning is a critical adaptive mechanism that enables the association of an environmental cue (the conditioned stimulus, CS) with a potential threat (the unconditioned stimulus, US), even when t...
www.biorxiv.org
August 8, 2025 at 4:05 PM
1/ Excited to share a new preprint!
Our latest study uncovers how serotonin precisely controls the “time window” for fear learning, ensuring that our brains link cues (CS) & threats (US) only when it’s adaptive.
#Neuroscience #FearLearning
www.biorxiv.org/content/10.1...
Our latest study uncovers how serotonin precisely controls the “time window” for fear learning, ensuring that our brains link cues (CS) & threats (US) only when it’s adaptive.
#Neuroscience #FearLearning
www.biorxiv.org/content/10.1...
Reposted by Zhipeng Huang
zip: Reducing Proof Sizes for Hash-Based SNARGs (Giacomo Fenzi, Yuwen Zhang) ia.cr/2025/1446
August 12, 2025 at 7:42 PM
zip: Reducing Proof Sizes for Hash-Based SNARGs (Giacomo Fenzi, Yuwen Zhang) ia.cr/2025/1446
Reposted by Zhipeng Huang
Very excited to release a new blog post that formalizes what it means for data to be compositional, and shows how compositionality can exist at multiple scales. Early days, but I think there may be significant implications for AI. Check it out! ericelmoznino.github.io/blog/2025/08...
Defining and quantifying compositional structure
What is compositionality? For those of us working in AI or cognitive neuroscience this question can appear easy at first, but becomes increasingly perplexing the more we think about it. We aren’t shor...
ericelmoznino.github.io
August 18, 2025 at 8:46 PM
Very excited to release a new blog post that formalizes what it means for data to be compositional, and shows how compositionality can exist at multiple scales. Early days, but I think there may be significant implications for AI. Check it out! ericelmoznino.github.io/blog/2025/08...
Reposted by Zhipeng Huang
Attractors are usually not mechanisms - new blog post: open.substack.com/pub/kording/...
Attractors are usually not mechanisms
The mathematical objects can not be. And the "attractor models" have not been established as mechanisms in mammals
open.substack.com
July 8, 2025 at 2:40 PM
Attractors are usually not mechanisms - new blog post: open.substack.com/pub/kording/...
Reposted by Zhipeng Huang
Together with @repromancer.bsky.social, I have been musing for a while that the exponentiated gradient algorithm we've advocated for comp neuro would work well with low-precision ANNs.
This group got it working!
arxiv.org/abs/2506.17768
May be a great way to reduce AI energy use!!!
#MLSky 🧪
This group got it working!
arxiv.org/abs/2506.17768
May be a great way to reduce AI energy use!!!
#MLSky 🧪
Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks
Studies in neuroscience have shown that biological synapses follow a log-normal distribution whose transitioning can be explained by noisy multiplicative dynamics. Biological networks can function sta...
arxiv.org
July 9, 2025 at 2:34 PM
Together with @repromancer.bsky.social, I have been musing for a while that the exponentiated gradient algorithm we've advocated for comp neuro would work well with low-precision ANNs.
This group got it working!
arxiv.org/abs/2506.17768
May be a great way to reduce AI energy use!!!
#MLSky 🧪
This group got it working!
arxiv.org/abs/2506.17768
May be a great way to reduce AI energy use!!!
#MLSky 🧪
Reposted by Zhipeng Huang
👨🎓🧾✨#icml2025 Paper: TabICL, A Tabular Foundation Model for In-Context Learning on Large Data
With Jingang Qu, @dholzmueller.bsky.social, and Marine Le Morvan
TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable
On top, it's 100% open source
1/9
With Jingang Qu, @dholzmueller.bsky.social, and Marine Le Morvan
TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable
On top, it's 100% open source
1/9
July 9, 2025 at 6:42 PM
👨🎓🧾✨#icml2025 Paper: TabICL, A Tabular Foundation Model for In-Context Learning on Large Data
With Jingang Qu, @dholzmueller.bsky.social, and Marine Le Morvan
TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable
On top, it's 100% open source
1/9
With Jingang Qu, @dholzmueller.bsky.social, and Marine Le Morvan
TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable
On top, it's 100% open source
1/9
Reposted by Zhipeng Huang
(1/3) Excited to introduce our new GRAB sensors for a series of steroid hormones! These tools enable real-time detection of steroid hormone dynamics in vivo🐭🧠. Happy to share these sensors and welcome any feedback! Please contact yulonglilab2018@gmail.com for information.
July 10, 2025 at 3:15 PM
(1/3) Excited to introduce our new GRAB sensors for a series of steroid hormones! These tools enable real-time detection of steroid hormone dynamics in vivo🐭🧠. Happy to share these sensors and welcome any feedback! Please contact yulonglilab2018@gmail.com for information.
Reposted by Zhipeng Huang
1/3) This may be a very important paper, it suggests that there are no prediction error encoding neurons in sensory areas of cortex:
www.biorxiv.org/content/10.1...
I personally am a big fan of the idea that cortical regions (allo and neo) are doing sequence prediction.
But...
🧠📈 🧪
www.biorxiv.org/content/10.1...
I personally am a big fan of the idea that cortical regions (allo and neo) are doing sequence prediction.
But...
🧠📈 🧪
Sensory responses of visual cortical neurons are not prediction errors
Predictive coding is theorized to be a ubiquitous cortical process to explain sensory responses. It asserts that the brain continuously predicts sensory information and imposes those predictions on lo...
www.biorxiv.org
July 11, 2025 at 3:45 PM
1/3) This may be a very important paper, it suggests that there are no prediction error encoding neurons in sensory areas of cortex:
www.biorxiv.org/content/10.1...
I personally am a big fan of the idea that cortical regions (allo and neo) are doing sequence prediction.
But...
🧠📈 🧪
www.biorxiv.org/content/10.1...
I personally am a big fan of the idea that cortical regions (allo and neo) are doing sequence prediction.
But...
🧠📈 🧪
Reposted by Zhipeng Huang
I am very proud to present you the first paper from the main research line of my group at the @mpiage.bsky.social in collaboration with my current group @molepi.bsky.social @bds-lumc.bsky.social at the LUMC, which is now published in @geroscience.bsky.social!
link.springer.com/article/10.1...
link.springer.com/article/10.1...
Functional characterisation of rare variants in genes encoding the MAPK/ERK signalling pathway identified in long-lived Leiden Longevity Study participants - GeroScience
Human longevity, which is coupled to compression of age-related disease, is a heritable trait. However, only few common genetic variants have been linked to longevity, suggesting that rare, family-spe...
link.springer.com
May 29, 2025 at 7:50 PM
I am very proud to present you the first paper from the main research line of my group at the @mpiage.bsky.social in collaboration with my current group @molepi.bsky.social @bds-lumc.bsky.social at the LUMC, which is now published in @geroscience.bsky.social!
link.springer.com/article/10.1...
link.springer.com/article/10.1...
Reposted by Zhipeng Huang
Super excited to see this paper from Armin Lak & colleagues out! (I've seen @saxelab.bsky.social present it before.)
www.cell.com/cell/fulltex...
tl;dr: The learning trajectories that individual mice take correspond to different saddle points in a deep net's loss landscape.
🧠📈 🧪 #NeuroAI
www.cell.com/cell/fulltex...
tl;dr: The learning trajectories that individual mice take correspond to different saddle points in a deep net's loss landscape.
🧠📈 🧪 #NeuroAI
Dopamine encodes deep network teaching signals for individual learning trajectories
Longitudinal tracking of long-term learning behavior and striatal dopamine reveals
that dopamine teaching signals shape individually diverse yet systematic learning
trajectories, captured mathematical...
www.cell.com
July 10, 2025 at 6:29 PM
Super excited to see this paper from Armin Lak & colleagues out! (I've seen @saxelab.bsky.social present it before.)
www.cell.com/cell/fulltex...
tl;dr: The learning trajectories that individual mice take correspond to different saddle points in a deep net's loss landscape.
🧠📈 🧪 #NeuroAI
www.cell.com/cell/fulltex...
tl;dr: The learning trajectories that individual mice take correspond to different saddle points in a deep net's loss landscape.
🧠📈 🧪 #NeuroAI
Reposted by Zhipeng Huang
Mitochondrial origins of the pressure to sleep
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Mitochondrial origins of the pressure to sleep - Nature
Research on Drosophila neurons shows links between the need to sleep and aerobic metabolism, indicating that the pressure to sleep may have a mitochondrial origin.
www.nature.com
July 16, 2025 at 10:57 PM
Mitochondrial origins of the pressure to sleep
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Zhipeng Huang
The 1st major study from @arc-cogitate.bsky.social
is out today in @nature.com—a landmark collaboration testing theories of consciousness through rigorous, preregistered science. Data & tools shared openly.
Contributed from @mcgillumedia.bsky.social @theneuro.bsky.social
nature.com/articles/s41...
is out today in @nature.com—a landmark collaboration testing theories of consciousness through rigorous, preregistered science. Data & tools shared openly.
Contributed from @mcgillumedia.bsky.social @theneuro.bsky.social
nature.com/articles/s41...
Adversarial testing of global neuronal workspace and integrated information theories of consciousness - Nature
Multimodal results (iEEG, fMRI and MEG) of predictions from integrated information theory and global neuronal workspace theory align with some predictions of both theories on visual consciou...
www.nature.com
April 30, 2025 at 3:12 PM
The 1st major study from @arc-cogitate.bsky.social
is out today in @nature.com—a landmark collaboration testing theories of consciousness through rigorous, preregistered science. Data & tools shared openly.
Contributed from @mcgillumedia.bsky.social @theneuro.bsky.social
nature.com/articles/s41...
is out today in @nature.com—a landmark collaboration testing theories of consciousness through rigorous, preregistered science. Data & tools shared openly.
Contributed from @mcgillumedia.bsky.social @theneuro.bsky.social
nature.com/articles/s41...