Cole Hurwitz
@colehurwitz.bsky.social
AI Architect, Core AI, IBM | Agentic AI & AgentOps - find my posts on LinkedIn
We are hiring on the IBM Core AI team. Feel free to DM me. π Job posting form - forms.gle/zZ2FHDg5sPVq...
Our group builds the technology that makes agentic AI reliable, observable, and governable at enterprise scale, with open research and tooling for evaluating agents and improving them.
Our group builds the technology that makes agentic AI reliable, observable, and governable at enterprise scale, with open research and tooling for evaluating agents and improving them.
forms.gle
December 3, 2025 at 10:13 PM
We are hiring on the IBM Core AI team. Feel free to DM me. π Job posting form - forms.gle/zZ2FHDg5sPVq...
Our group builds the technology that makes agentic AI reliable, observable, and governable at enterprise scale, with open research and tooling for evaluating agents and improving them.
Our group builds the technology that makes agentic AI reliable, observable, and governable at enterprise scale, with open research and tooling for evaluating agents and improving them.
After nearly a decade in academia, I am thrilled to share my next chapter: I am joining IBM as an AI Architect in the new Core AI group.
We are building an AgentOps platform to observe, evaluate, and optimize enterprise AI agents and we are hiring. DM me if interested.
We are building an AgentOps platform to observe, evaluate, and optimize enterprise AI agents and we are hiring. DM me if interested.
November 17, 2025 at 7:32 PM
After nearly a decade in academia, I am thrilled to share my next chapter: I am joining IBM as an AI Architect in the new Core AI group.
We are building an AgentOps platform to observe, evaluate, and optimize enterprise AI agents and we are hiring. DM me if interested.
We are building an AgentOps platform to observe, evaluate, and optimize enterprise AI agents and we are hiring. DM me if interested.
Reposted by Cole Hurwitz
Very happy for this to finally be published! We developed new machine learning methods for scalable mapping of synaptic connectivity using holographic optogenetics and compressed sensing.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
A pair of papers on using holographic optogenetics and compressed sensing for connectomics:
Rapid learning of neural circuitry from holographic ensemble stimulation enabled by model-based compressed sensing
www.nature.com/articles/s41...
Rapid learning of neural circuitry from holographic ensemble stimulation enabled by model-based compressed sensing
www.nature.com/articles/s41...
Rapid learning of neural circuitry from holographic ensemble stimulation enabled by model-based compressed sensing - Nature Neuroscience
The authors develop a new computational system for high-throughput mapping of synaptic connectivity using two-photon holographic optogenetics and intracellular recordings.
www.nature.com
September 29, 2025 at 7:26 PM
Very happy for this to finally be published! We developed new machine learning methods for scalable mapping of synaptic connectivity using holographic optogenetics and compressed sensing.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Cole Hurwitz
We present our preprint on ViV1T, a transformer for dynamic mouse V1 response prediction. We reveal novel response properties and confirm them in vivo.
With @wulfdewolf.bsky.social, Danai Katsanevaki, @arnoonken.bsky.social, @rochefortlab.bsky.social.
Paper and code at the end of the thread!
π§΅1/7
With @wulfdewolf.bsky.social, Danai Katsanevaki, @arnoonken.bsky.social, @rochefortlab.bsky.social.
Paper and code at the end of the thread!
π§΅1/7
September 19, 2025 at 12:37 PM
We present our preprint on ViV1T, a transformer for dynamic mouse V1 response prediction. We reveal novel response properties and confirm them in vivo.
With @wulfdewolf.bsky.social, Danai Katsanevaki, @arnoonken.bsky.social, @rochefortlab.bsky.social.
Paper and code at the end of the thread!
π§΅1/7
With @wulfdewolf.bsky.social, Danai Katsanevaki, @arnoonken.bsky.social, @rochefortlab.bsky.social.
Paper and code at the end of the thread!
π§΅1/7
Reposted by Cole Hurwitz
Two flagship papers from the International Brain Laboratory, now out in βͺ@Nature.comβ¬:
π§ Brain-wide map of neural activity during complex behaviour: doi.org/10.1038/s41586-025-09235-0
π§ Brain-wide representations of prior information in mouse decision-making: doi.org/10.1038/s41586-025-09226-1 +
π§ Brain-wide map of neural activity during complex behaviour: doi.org/10.1038/s41586-025-09235-0
π§ Brain-wide representations of prior information in mouse decision-making: doi.org/10.1038/s41586-025-09226-1 +
September 3, 2025 at 4:22 PM
Two flagship papers from the International Brain Laboratory, now out in βͺ@Nature.comβ¬:
π§ Brain-wide map of neural activity during complex behaviour: doi.org/10.1038/s41586-025-09235-0
π§ Brain-wide representations of prior information in mouse decision-making: doi.org/10.1038/s41586-025-09226-1 +
π§ Brain-wide map of neural activity during complex behaviour: doi.org/10.1038/s41586-025-09235-0
π§ Brain-wide representations of prior information in mouse decision-making: doi.org/10.1038/s41586-025-09226-1 +
Excited to co-organize our NeurIPS 2025 workshop on Foundation Models for the Brain and Body!
We welcome work across ML, neuroscience, and biosignals β from new approaches to large-scale models. Submit your paper or demo! π§ π§ͺ π¦Ύ
We welcome work across ML, neuroscience, and biosignals β from new approaches to large-scale models. Submit your paper or demo! π§ π§ͺ π¦Ύ
Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025! π§ π π§ͺ
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 π brainbodyfm-workshop.github.io
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 π brainbodyfm-workshop.github.io
July 11, 2025 at 7:51 PM
Excited to co-organize our NeurIPS 2025 workshop on Foundation Models for the Brain and Body!
We welcome work across ML, neuroscience, and biosignals β from new approaches to large-scale models. Submit your paper or demo! π§ π§ͺ π¦Ύ
We welcome work across ML, neuroscience, and biosignals β from new approaches to large-scale models. Submit your paper or demo! π§ π§ͺ π¦Ύ
Reposted by Cole Hurwitz
Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025! π§ π π§ͺ
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 π brainbodyfm-workshop.github.io
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 π brainbodyfm-workshop.github.io
July 11, 2025 at 5:01 PM
Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025! π§ π π§ͺ
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 π brainbodyfm-workshop.github.io
We invite short papers or interactive demos on AI for neural, physiological or behavioral data.
Submit by Aug 22 π brainbodyfm-workshop.github.io
Neural Encoding and Decoding at Scale (NEDS) is now accepted to @icmlconf.bsky.social as a spotlight (top 2.6%)! π§ π§ͺ
Another step toward a foundation model of the mouse brain: "Neural Encoding and Decoding at Scale (NEDS)"
Trained on neural and behavioral data from 70+ mice, NEDS achieves state-of-the-art prediction of behavior (decoding) and neural responses (encoding) on held-out animals. π
Trained on neural and behavioral data from 70+ mice, NEDS achieves state-of-the-art prediction of behavior (decoding) and neural responses (encoding) on held-out animals. π
May 2, 2025 at 3:17 PM
Neural Encoding and Decoding at Scale (NEDS) is now accepted to @icmlconf.bsky.social as a spotlight (top 2.6%)! π§ π§ͺ
Super cool. π Exciting to see the practical use cases of electrical stimulation for treating neurological disorders
A trial will try to treat tinnitus in people who have only just developed persistent ringing or buzzing in the ears.
Newcastle University researchers funded by the American Tinnitus Association will use electrical brain stimulation & sound therapy.
π§ͺπ§ ππΌ #neuroskyence
www.bbc.co.uk/news/videos/...
Newcastle University researchers funded by the American Tinnitus Association will use electrical brain stimulation & sound therapy.
π§ͺπ§ ππΌ #neuroskyence
www.bbc.co.uk/news/videos/...
Newcastle University trial to tackle tinnitus before it takes hold
The Newcastle study gives both electrical stimulus and sound therapy to people with early tinnitus.
www.bbc.co.uk
May 1, 2025 at 3:36 PM
Super cool. π Exciting to see the practical use cases of electrical stimulation for treating neurological disorders
Reposted by Cole Hurwitz
Weβre hiring postdocs to join my lab at UNC. If youβre interested in adolescence, brain, and social development, DM me. Our work incorporates fMRI, social media, and longitudinal methods. We study risks and opportunities in adolescence. If youβre at #SRCD2025 and want to meet, please reach out!
April 30, 2025 at 7:31 PM
Weβre hiring postdocs to join my lab at UNC. If youβre interested in adolescence, brain, and social development, DM me. Our work incorporates fMRI, social media, and longitudinal methods. We study risks and opportunities in adolescence. If youβre at #SRCD2025 and want to meet, please reach out!
Reposted by Cole Hurwitz
I asked "on the other platform" what were the most important improvements to the original 2017 transformer.
That was quite popular and here is a synthesis of the responses:
That was quite popular and here is a synthesis of the responses:
April 28, 2025 at 6:47 AM
I asked "on the other platform" what were the most important improvements to the original 2017 transformer.
That was quite popular and here is a synthesis of the responses:
That was quite popular and here is a synthesis of the responses:
Whoever is at the @iclr-conf.bsky.social workshops, feel free to reach out to meet! Looking for fun neuro conversations since there arenβt any neuro workshops π’
April 27, 2025 at 1:54 AM
Whoever is at the @iclr-conf.bsky.social workshops, feel free to reach out to meet! Looking for fun neuro conversations since there arenβt any neuro workshops π’
Reposted by Cole Hurwitz
Scaling models across multiple animals was a major step toward building neuro-foundation models; the next frontier is enabling multi-task decoding to expand the scope of training data we can leverage.
Excited to share our #ICLR2025 Spotlight paper introducing POYO+ π§
poyo-plus.github.io
π§΅
Excited to share our #ICLR2025 Spotlight paper introducing POYO+ π§
poyo-plus.github.io
π§΅
POYO+
POYO+: Multi-session, multi-task neural decoding from distinct cell-types and brain regions
poyo-plus.github.io
April 25, 2025 at 10:14 PM
Scaling models across multiple animals was a major step toward building neuro-foundation models; the next frontier is enabling multi-task decoding to expand the scope of training data we can leverage.
Excited to share our #ICLR2025 Spotlight paper introducing POYO+ π§
poyo-plus.github.io
π§΅
Excited to share our #ICLR2025 Spotlight paper introducing POYO+ π§
poyo-plus.github.io
π§΅
Itβs been great working with you π
April 22, 2025 at 12:18 AM
Itβs been great working with you π
April 21, 2025 at 5:57 PM
Eva Dyer, Chandramouli Chandrasekaran, Nicholas A. Steinmetz, and Liam Paninski (ran out of characters!)
April 21, 2025 at 5:34 PM
Eva Dyer, Chandramouli Chandrasekaran, Nicholas A. Steinmetz, and Liam Paninski (ran out of characters!)
This work was led by @hanyu42.bsky.social who tirelessly worked to make this possible. In collaboration with Hanrui Lyu, Ethan Yixun Xu, @mostsquares.bsky.social, @kenjilee.bsky.social, Fan Yang, Andrew M. Shelton, Shawn Olsen, Sahar Minavi, Olivier Winter, @intlbrainlab.bsky.social, and
Han Yu (@hanyu42.bsky.social)
Ph.D. student at Columbia Center for Theoretical Neuroscience
hanyu42.bsky.social
April 21, 2025 at 5:34 PM
This work was led by @hanyu42.bsky.social who tirelessly worked to make this possible. In collaboration with Hanrui Lyu, Ethan Yixun Xu, @mostsquares.bsky.social, @kenjilee.bsky.social, Fan Yang, Andrew M. Shelton, Shawn Olsen, Sahar Minavi, Olivier Winter, @intlbrainlab.bsky.social, and
We are still working on the codebase and aim to release a tool soon that users can download, fine-tune, and apply to their own datasets!
April 21, 2025 at 5:34 PM
We are still working on the codebase and aim to release a tool soon that users can download, fine-tune, and apply to their own datasets!
We evaluate NEMO on brain region localization by predicting the region of individual neurons (and nearby groups) using only the extracted features, and compare it to baseline methods.
NEMO again outperforms both the VAE-based and supervised approaches.
NEMO again outperforms both the VAE-based and supervised approaches.
April 21, 2025 at 5:34 PM
We evaluate NEMO on brain region localization by predicting the region of individual neurons (and nearby groups) using only the extracted features, and compare it to baseline methods.
NEMO again outperforms both the VAE-based and supervised approaches.
NEMO again outperforms both the VAE-based and supervised approaches.
We scale NEMO to the full IBL Brain-Wide Map dataset: 675 insertions from over 100 animals, yielding 37,017 high-quality neurons.
Without using any labels, NEMO's features align closely with anatomical regions and are consistent across labs.
Without using any labels, NEMO's features align closely with anatomical regions and are consistent across labs.
April 21, 2025 at 5:34 PM
We scale NEMO to the full IBL Brain-Wide Map dataset: 675 insertions from over 100 animals, yielding 37,017 high-quality neurons.
Without using any labels, NEMO's features align closely with anatomical regions and are consistent across labs.
Without using any labels, NEMO's features align closely with anatomical regions and are consistent across labs.
We benchmark NEMO against two SOTA cell-type classification methods, PhysMAP and a VAE (Beau et al., 2025), using two optotagged datasets from the mouse cerebellum and visual cortex.
NEMO outperforms all baselines, including fully supervised models, with minimal fine-tuning.
NEMO outperforms all baselines, including fully supervised models, with minimal fine-tuning.
April 21, 2025 at 5:34 PM
We benchmark NEMO against two SOTA cell-type classification methods, PhysMAP and a VAE (Beau et al., 2025), using two optotagged datasets from the mouse cerebellum and visual cortex.
NEMO outperforms all baselines, including fully supervised models, with minimal fine-tuning.
NEMO outperforms all baselines, including fully supervised models, with minimal fine-tuning.
We construct a paired dataset of spike trains and waveforms for all neurons, transforming spiking activity into an ACG image (Beau et al., 2025) that captures autocorrelation across firing rates.
NEMO is trained to align ACGs and waveforms in a shared embedding space.
NEMO is trained to align ACGs and waveforms in a shared embedding space.
April 21, 2025 at 5:34 PM
We construct a paired dataset of spike trains and waveforms for all neurons, transforming spiking activity into an ACG image (Beau et al., 2025) that captures autocorrelation across firing rates.
NEMO is trained to align ACGs and waveforms in a shared embedding space.
NEMO is trained to align ACGs and waveforms in a shared embedding space.
Building on current multimodal cell-type classification methods (Lee et al. 2024 and Beau et al. 2025), we introduce a contrastive learning method for spiking activity and extracellular waveforms called NEMO. π
Paper: Paper: openreview.net/forum?id=10J...
Website: ibl-nemo.github.io
Paper: Paper: openreview.net/forum?id=10J...
Website: ibl-nemo.github.io
In vivo cell-type and brain region classification via multimodal...
Current electrophysiological approaches can track the activity of many neurons, yet it is usually unknown which cell-types or brain areas are being recorded without further molecular or...
openreview.net
April 21, 2025 at 5:34 PM
Building on current multimodal cell-type classification methods (Lee et al. 2024 and Beau et al. 2025), we introduce a contrastive learning method for spiking activity and extracellular waveforms called NEMO. π
Paper: Paper: openreview.net/forum?id=10J...
Website: ibl-nemo.github.io
Paper: Paper: openreview.net/forum?id=10J...
Website: ibl-nemo.github.io
Thrilled to share our state-of-the-art method for in vivo cell-type classification and brain region localization, NEMO, which is now now a spotlight at @iclr-conf.bsky.social !
We use NEMO to characterize the electrophysiological diversity of cell-types across the entire mouse brain. π π§ͺ π§
We use NEMO to characterize the electrophysiological diversity of cell-types across the entire mouse brain. π π§ͺ π§
April 21, 2025 at 5:34 PM
Thrilled to share our state-of-the-art method for in vivo cell-type classification and brain region localization, NEMO, which is now now a spotlight at @iclr-conf.bsky.social !
We use NEMO to characterize the electrophysiological diversity of cell-types across the entire mouse brain. π π§ͺ π§
We use NEMO to characterize the electrophysiological diversity of cell-types across the entire mouse brain. π π§ͺ π§
Reposted by Cole Hurwitz
Agreed! But here's a note of caution: in the brain, different behavioral contexts can engage completely different neurons! Julie Lee in our lab published this in 2022 (and I'm still digesting the implications).
"Task specificity in mouse parietal cortex"
www.cell.com/neuron/fullt...
"Task specificity in mouse parietal cortex"
www.cell.com/neuron/fullt...
Redirecting
doi.org
April 18, 2025 at 9:32 PM
Agreed! But here's a note of caution: in the brain, different behavioral contexts can engage completely different neurons! Julie Lee in our lab published this in 2022 (and I'm still digesting the implications).
"Task specificity in mouse parietal cortex"
www.cell.com/neuron/fullt...
"Task specificity in mouse parietal cortex"
www.cell.com/neuron/fullt...