Sign in

Weinan Sun

@sunw37.bsky.social
259 followers 64 following 25 posts

Neuroscience, Artificial Intelligence, and Beyond. Assistant professor at Cornell Dept. of Neurobiology & Behavior

PostsRepliesMedia
Weinan Sun @sunw37.bsky.social · 17/02/2026
thank you, Pierre!!
000
Weinan Sun @sunw37.bsky.social · 17/02/2026
Paper: biorxiv.org/content/10.64898/2026.02.13.705771v1 Code: github.com/Sun-Lab-NBB/ataraxis
github.com
GitHub - Sun-Lab-NBB/ataraxis: Entry point and documentation hub for the Ataraxis science-automation framework.
Entry point and documentation hub for the Ataraxis science-automation framework. - Sun-Lab-NBB/ataraxis
120
Weinan Sun @sunw37.bsky.social · 17/02/2026
Everything is open-source and designed as building blocks. We're relicensing under Apache 2.0 in the coming weeks to make adoption even easier. If your science hits a wall at the hardware layer, this is for you.
120
Weinan Sun @sunw37.bsky.social · 17/02/2026
Key design choice: AI helps at configuration time only. During actual experiments, everything runs deterministically with no AI in the loop. Network goes down? API rate limited? Doesn't matter - your experiment keeps running.
100
Weinan Sun @sunw37.bsky.social · 17/02/2026
@inkaroseng.bsky.social also built a centralized marketplace hub for our agentic skills with native Claude Code integration, enforcing our lab's conventions across all projects.
100
Weinan Sun @sunw37.bsky.social · 17/02/2026
We built standardized Python/C++/C# libraries for common lab hardware - cameras, microcontrollers, motors, timing - that all follow the same interface pattern. Then exposed them to Claude Code through @anthropic.com's MCP servers. cc @bcherny.bsky.social
100
Weinan Sun @sunw37.bsky.social · 17/02/2026
The problem: AI coding assistants can't discover what hardware is on your rig, diagnose why a device isn't responding, or help integrate a new instrument. Closing this gap is essential for automated laboratories.
210
Weinan Sun @sunw37.bsky.social · 17/02/2026
Paper: biorxiv.org/content/10.64898/2026.02.13.705771v1 Code: github.com/Sun-Lab-NBB/ataraxis Video demos: 🎥 Pre-session validation: youtu.be/Ui2AEvFkCoE 🎥 Hardware troubleshooting: youtu.be/KBgv4zgwwKw 🎥 AI-guided integration: youtu.be/iemcuTz1_iM
youtu.be
Ataraxis Demo 2: Hardware Troubleshooting & Experiment Setup
YouTube video by Weinan Sun
110
Weinan Sun @sunw37.bsky.social · 17/02/2026
Closed-loop AI scientists will need to talk to lab hardware. We released Ataraxis - an open-source framework giving AI coding assistants direct access to physical instruments. biorxiv.org/content/10.64898/2026.02.13.705771v1 Built by our talented Ph.D. student @inkaroseng.bsky.social at Cornell. 🧵
biorxiv.org
140
Reposted by Weinan Sun
Virginie M. S. Ruetten @vmsruetten.bsky.social · 08/09/2025
Thanks Misha for the shout-out! It has been a truly mind-opening journey. WHOLISTIC is one step towards whole-organism neuroscience and a true physiological observatory - with extensions on the way! I am continually amazed by what the data reveals - so much remains to be discovered and mined.
25212
Reposted by Weinan Sun
LaurenGuillette.bsky.social @laurenguillette.bsky.social · 23/05/2025
New #Outlook #PsynomLB 'Emergence of orthogonal hippocampal representations during spatial learning' bit.ly/4mlOXQa by Prof. Vern Bingman @BGSU_Biology about the recent paper bit.ly/4jZO0eT by @sunw37 @JohanWinn @CornellNBB et al. @nature @Psychonomic_Soc
bit.ly
Emergence of orthogonal hippocampal representations during spatial learning
Learning & Behavior - Sun et al. (2025) reveal the progressive, dynamic changes in the response properties of thousands of hippocampal neurons as mice learn a conditional discrimination while...
011
Reposted by Weinan Sun
AntonioFR @antferrui.bsky.social · 17/03/2025
Excited to share our latest story! We found disentangled memory representations in the hippocampus that generalized across time and environments, despite the seemingly random drift and remapping of single cells. This code enabled the transfer of prior knowledge to solve new tasks
614958
Reposted by Weinan Sun
Dileep George @dileeplearning @dileeplearning.bsky.social · 14/03/2025
It was fun to visit Weinan's lab @sunw37.bsky.social at Cornell to give this talk. Exciting to see the experiments he's cooking up, and we had lots of fun discussions about PFC, hippocampus, consciousness and meditation! Part of the talk content is here: blog.dileeplearning.com/p/space-is-a...
2182
Reposted by Weinan Sun
Kristin Branson @kristinmbranson.bsky.social · 14/02/2025
We read "Large Concept Models" in our reading group. It models language at the sentence resolution - "concepts". We had lots of thoughts about it! You can read them in our new Janelia CVML blog post: janelia-cvml.github.io/blog/posts/L... #ML #AI #Janelia @adjavon.bsky.social @bogovicj.bsky.social
janelia-cvml.github.io
Large Concept Models: Language Modeling in a Sentence Representation Space – Janelia CVML
Summary of and thoughts on Meta’s recent paper
1167
Reposted by Weinan Sun
Jason Keller @neurojak.bsky.social · 13/02/2025
(1/11) Today I preprinted a lot of work from my postdoc with @dudman.bsky.social, which started with a question of how the nervous system balances flexibility with efficiency of learning. The thread below gives some background.... www.biorxiv.org/content/10.1...
biorxiv.org
Cortical control of innate behavior from subcortical demonstration
Motor control in mammals is traditionally viewed as a hierarchy of descending spinal-targeting pathways, with frontal cortex at the top. Many redundant muscle patterns can solve a given task, and this...
45924
Reposted by Weinan Sun
mark cembrowski @markcembrowski.bsky.social · 13/02/2025
delighted to share our work revealing a new type of excitatory hippocampal neuron we call the "ovoid cell", which has really exquisite properties relative to adjacent pyramidal cells! superb work of first-author @adriennekinman.bsky.social and many others in the lab www.nature.com/articles/s41...
nature.com
Atypical hippocampal excitatory neurons express and govern object memory - Nature Communications
Pyramidal cells are classically thought to comprise the excitatory output of the subiculum. Here, the authors show the existence of “ovoid cells”, excitatory subiculum neurons with specialized gene ex...
912645
Reposted by Weinan Sun
Carsen Stringer @computingnature.bsky.social · 12/02/2025
#Cellpose 3 paper now out. Not all images are perfect. Restore your images with Cellpose3 to get better segmentations, w/ @marius10p.bsky.social www.nature.com/articles/s41...
613749
Reposted by Weinan Sun
Alex Kwan @alexkwan.bsky.social · 13/02/2025
Can whole-brain imaging of cellular c-Fos signals be used to classify #psychedelics? 🧠🔬💊 Our study by @aboharbf.bsky.social and @pashadavoudian.bsky.social, developing an imaging and machine learning pipeline to test a panel of psychoactive drugs. Paper here 👇 www.nature.com/articles/s41...
nature.com
Classification of psychedelics and psychoactive drugs based on brain-wide imaging of cellular c-Fos expression - Nature Communications
A challenge in psychiatric drug discovery is to predict the therapeutic potential of a novel compound. Here, the authors show that brain-wide imaging of immediate early gene expression can be used to ...
512344
Reposted by Weinan Sun
nspruston.bsky.social @nspruston.bsky.social · 13/02/2025
I’m excited about this collaborative project by @sunw37.bsky.social, @johanwinn.bsky.social, and many other talented contributors. Read about how our @hhmijanelia.bsky.social team imaged thousands of neurons in mouse hippocampus as mice learned cognitive tasks over several days: hhmi.news/4hXIp7r
hhmi.news
Mapmaking in the mind: new research details how the brain builds mental maps of the world
To see how cognitive maps form in the brain, researchers used a Janelia-designed, high-resolution microscope with a large field of view to image neural activity in thousands of neurons in the
03913
Weinan Sun @sunw37.bsky.social · 13/02/2025
thank you Dileep for the huge inspiration!
010
Reposted by Weinan Sun
Dileep George @dileeplearning @dileeplearning.bsky.social · 13/02/2025
Must-read for anyone interested in cognitive maps & the hippocampus.
2196
Reposted by Weinan Sun
Ezekiel Williams @ezekielwilliams.bsky.social · 12/02/2025
Do I like this so much because it's a fantastic bit of science or because it's a fantastic job of doing science communication?!? Probably both. Regardless, awesome work that is worth checking out:)
052
Weinan Sun @sunw37.bsky.social · 12/02/2025
sounds great! hope to catch up soon :)
010
Weinan Sun @sunw37.bsky.social · 12/02/2025
Thank you, Dan! Hope you are well!
110
Reposted by Weinan Sun
PessoaBrain @pessoabrain.bsky.social · 12/02/2025
Fantastic video explaining a study of hippocampal map formation.
1246
Weinan Sun @sunw37.bsky.social · 12/02/2025
Thank you, Tim!!!
110
Reposted by Weinan Sun
Tim Behrens @behrenstimb.bsky.social · 12/02/2025
Great fun!!!
1112
Weinan Sun @sunw37.bsky.social · 12/02/2025
12/12 This work wouldn’t be possible without co-first author @johanwinn.bsky.social, mentor @nspruston.bsky.social, and co-authors Maanasa, Chongxi, Koichiro, Arco, Michalis, Rachel, @computingnature.bsky.social, Dan, and James, plus many others (see Acknowledgments), and support from @HHMIJanelia!
030
Weinan Sun @sunw37.bsky.social · 12/02/2025
11/12 In summary, our work offers a dataset on how hippocampal cognitive maps form, revealing how brains build mental models and shedding light on learning algorithms—which could guide biologically inspired AI that reason using naturally formed internal world models.
110
Weinan Sun @sunw37.bsky.social · 12/02/2025
10/12 Our data support prior work on multiple hippocampal representations for ambiguous inputs (e.g., Eichenbaum, @dileeplearning.bsky.social, @behrenstimb.bsky.social, @jcrwhittington.bsky.social). See our paper and preprint for more foundational references!
150
Weinan Sun @sunw37.bsky.social · 12/02/2025
9/12 What do our findings reveal about hippocampal computation? We tested several models—but only Clone-Structured Causal Graph (CSCG) @dileeplearning.bsky.social matched the orthogonalized states and learning trajectory, highlighting hidden-state inference as a key learning principle.
161
Weinan Sun @sunw37.bsky.social · 12/02/2025
8/12 At the single-cell level, cells in expert mice showed a continuum: some cells were “place-like,” while others became “splitters” firing selectively for Near vs. Far trials. Single-cell responses evolve across sessions, driving overall decorrelation. Explore our data: cognitivemap.janelia.org
120
Weinan Sun @sunw37.bsky.social · 12/02/2025
7/12 The final representation resembled a state machine. In ambiguous areas, CA1 activity split into distinct latent states for Near vs. Far corridors. When cues or track lengths changed, the map flexibly adapted.
110
Weinan Sun @sunw37.bsky.social · 12/02/2025
6/12 Using UMAP on our data, the CA1 manifold evolved over learning. It started as an unstructured cluster, then formed a hub-and-spoke, and finally a ring that split into branches by trial type—refining similar inputs into distinct states that eventually capture the underlying task structure.
220
Weinan Sun @sunw37.bsky.social · 12/02/2025
5/12 During learning, hippocampal activity became more distinct. Early on, neurons in ambiguous zones responded similarly; over time, responses separated and tuned to specific task states.
130
Weinan Sun @sunw37.bsky.social · 12/02/2025
4/12 During training, mice showed 4 behavioral strategies: 1. Random licking, 2. Licking at both potential rewards, 3. Stopping after collecting a reward, 4. Only licking at the correct reward location.
110
Weinan Sun @sunw37.bsky.social · 12/02/2025
3/12 Task: Mice ran along two similar VR corridors—one with a Near reward and one with a Far reward. An indicator cue at the start signaled the active corridor. Expert mice learned to lick only at the correct reward zone.
110
Weinan Sun @sunw37.bsky.social · 12/02/2025
2/12 We used a custom 2P-RAM mesoscope (designed by @sofroniewn.bsky.social, Dan Flickinger, & Karel Svoboda. @hhmijanelia.bsky.social) to track thousands of CA1 cells across sessions. It let us see changes in single-cell & population activity throughout learning.
120
Weinan Sun @sunw37.bsky.social · 12/02/2025
1/12 How do animals build an internal map? In our new paper, we tracked thousands of mouse CA1 neurons over days/weeks as they learned a VR navigation task. @nspruston.bsky.social & co-1st author @johanwinn.bsky.social Video: www.youtube.com/watch?v=yw_4... Paper: www.nature.com/articles/s41...
youtube.com
Learning produces an orthogonalized state machine in the hippocampus
YouTube video by Weinan Sun
419066
Reposted by Weinan Sun
Josh Dudman @dudman.bsky.social · 12/09/2023
Come lead a group at Janelia, be our neighbor. Nov 1 deadline for this round www.janelia.org/our-research...
043
Reposted by Weinan Sun
Melanie Mitchell @melaniemitchell.bsky.social · 11/09/2023
My latest Substack post: Can Large Language Models Reason? aiguide.substack.com/p/can-large-...
aiguide.substack.com
Can Large Language Models Reason?
What should we believe about the reasoning abilities of today’s large language models? As the headlines above illustrate, there’s a debate raging over whether these enormous pre-trained neural net...
14716