Cole Hurwitz
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. 🙂 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.
- 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.
- Reposted by Cole HurwitzVery 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...
- 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...
- Reposted by Cole HurwitzWe 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! 🧵1/7
- Reposted by Cole HurwitzTwo flagship papers from the International Brain Laboratory, now out in @Nature.com: 🧠 Brain-wide map of neural activity during complex behaviour: doi.org/10.1038/s41586-025-09235-0 🧠 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 — from new approaches to large-scale models. Submit your paper or demo! 🧠 🧪 🦾
- Excited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025! 🧠📈 🧪 We invite short papers or interactive demos on AI for neural, physiological or behavioral data. Submit by Aug 22 👉 brainbodyfm-workshop.github.io
- Reposted by Cole HurwitzExcited to announce the Foundation Models for the Brain and Body workshop at #NeurIPS2025! 🧠📈 🧪 We invite short papers or interactive demos on AI for neural, physiological or behavioral data. Submit by Aug 22 👉 brainbodyfm-workshop.github.io
- Neural Encoding and Decoding at Scale (NEDS) is now accepted to @icmlconf.bsky.social as a spotlight (top 2.6%)! 🧠 🧪
- Super cool. 😀 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. 🧪🧠👂🏼 #neuroskyence www.bbc.co.uk/news/videos/...
- Reposted by Cole HurwitzWe’re hiring postdocs to join my lab at UNC. If you’re 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 you’re at #SRCD2025 and want to meet, please reach out!
- Reposted by Cole HurwitzI 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:
- Whoever is at the @iclr-conf.bsky.social workshops, feel free to reach out to meet! Looking for fun neuro conversations since there aren’t any neuro workshops 😢
- Reposted by Cole HurwitzScaling 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+ 🧠 poyo-plus.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. 🐭 🧪 🧠
- 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. 🐟 Paper: Paper: openreview.net/forum?id=10J... Website: ibl-nemo.github.io
- 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.
-
View full thread
- Reposted by Cole HurwitzAgreed! 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...
- Reposted by Cole HurwitzThanks so much for the shout-out, and congrats on your exciting work!! 🎉 🙂 Also, a good reminder to share that our work is now out in Cell Reports 🙏🎊 ⬇️ www.cell.com/cell-reports...
- Reposted by Cole HurwitzVery cool work here from @colehurwitz.bsky.social and others, and an important step towards a proper foundation model for neuroscience. Wonderful to see the scaling effects of moving from single session to multisession! (Also, a great use of the IBL data, IMO). #NeuroAI 🧠📈 🧪
- 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. 🐀
- Current neurofoundation modeling approaches focus on either predicting neuronal responses (Wang et al. 2025) or behavior (POYO, POYO+, NDT2). Inspired by Schulz et al. 2025, we unify these two tasks using a multimodal masked modeling approach we call "Neural Encoding and Decoding at Scale (NEDS)"
- We tokenize neural activity, continuous, and discrete behaviors at each time step and then feed them into our shared transformer-based encoder model. We train NEDS by masking out and reconstructing neural activity, behavior, within-modality, and across modalities.
-
View full threadAnd of course, I forgot the link to the paper: arxiv.org/abs/2504.08201
- Reposted by Cole HurwitzInterested in foundation models for #neuroscience? Want to contribute to the development of the next-generation of multi-modal models? Come join us at IVADO in Montreal! We're hiring a full-time machine learning specialist for this work. Please share widely! #NeuroAI 🧠📈 🧪
- 🔍 [Job Offer] #MachineLearning Specialist. Join the IVADO Research Regroupement - AI and Neuroscience (R1) to develop foundational models in the field of neuroscience. More info: ivado.ca/2025/04/08/s... #JobOffer #AI #Neuroscience #Research #MachineLearning
- Amazing work led by @ninelk.bsky.social. This work introduces BAND, a new approach for modeling the dynamics underlying neural and behavioral data. Using this approach, @ninelk.bsky.social was able to capture feedback-driven motor corrections which were previously missed!
- Reposted by Cole HurwitzI'll be giving a talk at the foundation model workshop #Cosyne2025 tomorrow: neurofm-workshop.github.io In response to @thetransmitter.bsky.social article by @tyrellturing.bsky.social & Eva Dyer I'll be talking about: How do "foundation"/AI models help us (experimenters) study the brain?
- Reposted by Cole HurwitzEva Dyer and I wrote an opinion piece for @thetransmitter.bsky.social on why neuroscience needs to embrace complexity and accept the "bitter lesson" by using a data-driven regime at scale. With commentary from several wonderful researchers! 🧠📈 #NeuroAI 🧪
- How can we make progress in developing a general model of neural computation rather than a series of disjointed models tied to specific experimental circumstances, ask Eva Dyer and @tyrellturing.bsky.social in the latest entry in our NeuroAI series. www.thetransmitter.org/neuroai/acce...
- Cosyne is this week! Looking forward to catching up with whoever is there. :-) #Cosyne2025 If you are sticking around for workshops, come checkout our 2-day workshop on building foundation models for the brain: neurofm-workshop.github.io 🧠 🧪
- The International Brain Laboratory reproducibility platform paper is now published at eLife. An amazing effort by many different labs and individuals to understand and improve the reproducibility of electrophysiological measurements in mice. 🧠
- Reposted by Cole HurwitzJoin us at #COSYNE2025 to explore recent advancements in large-scale training and analysis of brain data! 🧠🟦 We also made a starter pack with (most of) our speakers: go.bsky.app/Ss6RaEF
- 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!
- Super excited to be co-organizing this. 😄 We have an amazing list of speakers and some fun panel discussions planned. Come join us!
- 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!
- Reposted by Cole Hurwitz"I think there's real risk of a generation or more of data being lost." - Dr. Michael Greicius, neurology professor at Stanford University, on the damage Trump's cuts to NIH research will do to progress on a treatment for Alzheimer's disease, adding as much as 20 years to the timeline.
- Reposted by Cole HurwitzPetition to Reverse the NIH Indirect Cost Cap. Sign and Circulate. Mobilize. Organize. chng.it/LS57Nk7r6k
- Reposted by Cole HurwitzThe overlapping activity in the animals’ nucleus accumbens may underpin pair bonding, a new preprint suggests. www.thetransmitter.org/social-behav... By @shaena.bsky.social 📹 Courtesy of Paul Muhlrad @wormpicker.bsky.social #neuroskyence
- Reposted by Cole HurwitzCurious how place cells adapt to uncertainty in reward location? We found that predictable changes boost “reward place cells” & warp hippocampal maps. Check out our new preprint: with Feng Xuan, Jack Mellor, Peter Dayan and Dan Dombeck: www.biorxiv.org/content/10.1...
- Amazing. Cognition is about 100,000,000 times slower than our sensory systems 🤯
- The unbearable slowness of being: Humans still clock in at just 10 bits/s. Even after peer review :) Share link: authors.elsevier.com/a/1kHVa3BtfH.... ArXiv: arxiv.org/abs/2408.10234
- Reposted by Cole HurwitzI promised to write about my thoughts on the status of the field of neuroAI, some of the big challenges we are facing, and the approaches we are taking to address them. This is super selective on the topic of finding a good model but in my view it affects the field as a whole. Here we go. 🧵
- Come check out our poster at #NeurIPS2024 (Thursday 11am PST in the East Exhibit Hall A-C). Excited to get feedback on our new direction for neurofoundation models. :-)
- Heading to #NeurIPS2024 next week. Looking forward to seeing everyone there!
- Reposted by Cole Hurwitz1/ We just open-sourced two large wrist electromyography (EMG) datasets - one towards typing without a keyboard and the other for predicting hand poses - with baselines. We believe these will help advance research into making high bandwidth non-invasive neuromotor interfaces a reality!
