Zuwan Lin retweeted
Can neurons speak? 🧠
New preprint: NEURRATOR. We take #MechInterp out of the LMs and point it at real brains with real neurons. We read spike trains from single neurons in mouse visual cortex and get them to narrate the scene in plain language. 🧵
#NeuroAI #interpretability #neuroscience #LLMs #compneuro #SAEs #Neuropixels #AI
Zuwan Lin retweeted
An autonomous AI agent for universal behavior analysis biorxiv.org/content/10.1101/… #biorxiv_neursci
Zuwan Lin retweeted
We are very excited to share a preprint for our @BehaveAIAgent , the first fully autonomous AI agent for universal behavior analysis. BehaveAgent is the result of rewarding work with @ZuwanLin and the amazing team in @ganoopyliujia lab at @Harvard .
1/6
biorxiv.org/content/10.1101/…
Zuwan Lin retweeted
Zuwan Lin ... Jia Liu introduced the Spatial Transcriptomics AI Agent that integrates multimodal LLMs with specialized computational tools to transform weeks-long analysis tasks into minutes of automated processing. ➡ biorxiv.org/content/10.1101/…
#singlecell #spatialomics – at Tomsk, Russia
Zuwan Lin retweeted
🚨Preprint alert #1🚨AI-driven spatial transcriptomics for a SC-pancreas transplant test case - fantastic collaboration with @ganoopyliujia @wenbowang11 @ZuwanLin - checkout the youtube demo!
Thrilled to share our latest preprint regarding STAgent, a multimodal AI agent for spatial transcriptomics.:
(1/9) Check our manuscript at: biorxiv.org/content/10.1101/…
and demo at: youtu.be/aEUop05RINY
Zuwan Lin retweeted
Thrilled to share our latest preprint regarding STAgent, a multimodal AI agent for spatial transcriptomics.:
(1/9) Check our manuscript at: biorxiv.org/content/10.1101/…
and demo at: youtu.be/aEUop05RINY