Shailee Jain

@shaileejain.bsky.social

Neuro + ML + NLP Postdoc@Chang Lab, UCSF | Prev.: PhD@Huth Lab, UT Austin https://shaileesjain.github.io she/her 🧠🤖💬

How is uncertainty in LLMs output reflected in internal representations? In our new work (to appear at ICML 2026), we show that the shape of internal token trajectories provides a direct geometric link to behavioral uncertainty (output entropy). 🧵(1/n)

Preprint alert! We've done the first ever wireless brain recordings from the high-level visual & motor regions (IT/PMv/PFC) in monkeys engaged in natural behaviors as well as during controlled screen-based tasks. Read below for a lay summary and the link for details! 1/8

Bild

Thank you for inviting me! ☺️ Always great to chat about neuroscience, NLP and linguistics under one roof!

NYU Center for Data Science@nyudatascience.bsky.social · 4mo ago

UCSF postdoctoral researcher Shailee Jain (@shaileejain.bsky.social) recently visited CDS for the Minds, Brains and Machines Seminar. She discussed using AI interpretability tools and linguistic theory to better understand the human brain. Jain is at the Chang lab in UCSF's Dept of Neurosurgery.

"Neuroscientists need better training in computational methods." We got you. Join us in July: neuromatch.io/courses/ Our #ComputationalNeuroscience course is the perfect way to gain practical experience and build a strong foundation in this field.

The Transmitter @thetransmitter.bsky.social · 8mo ago

As neuroscience expands, @thetransmitter.bsky.social asks, how can neuroscience training programs best meet the needs of students and the field? See what survey respondents had to say: www.thetransmitter.org/training/how... #neuroskyence #StateOfNeuroscience

starting fall 2026 i'll be an assistant professor at @upenn.edu 🥳 my lab will develop scalable models/theories of human behavior, focused on memory and perception currently recruiting PhD students in psychology, neuroscience, & computer science! reach out if you're interested 😊

a red building on UPENN's campus photographed during the fallthe Philadelphia skyline, with clear skies and autumn trees

We are still accepting applications for the #postdoc opportunity in the lab 🕵‍♀️ 🧠 More details 👇 Postdoctoral position: lnkd.in/g4TkRxpM Research directions: lnkd.in/eV2iMKGf Our team and philosophy: lnkd.in/eh3nnNgq

LinkedIn

This link will take you to a page that’s not on LinkedIn

lnkd.in

Abhilasha Joshi, PhD@rhythmicspikes.bsky.social · last yr.

📣 We are expanding! Repost 🙏🏽 - Postdoc (funded by @simonsfoundation.org grant on synchronisation between cognitive representations and stepping) - Project Associates - Create your role! (Reach out if you are keen on these topics and these roles do not define you 👀🤗) www.neuroact.in

New paper with @mujianing.bsky.social & @prestonlab.bsky.social! We propose a simple model for human memory of narratives: we uniformly sample incoming information at a constant rate. This explains behavioral data much better than variable-rate sampling triggered by event segmentation or surprisal.

bioRxiv Neuroscience@biorxiv-neursci.bsky.social · last yr.

Efficient uniform sampling explains non-uniform memory of narrative stories https://www.biorxiv.org/content/10.1101/2025.07.31.667952v1

Our latest research on the neural basis of speech-motor sequencing is now published in @nathumbehav.nature.com! Check out this high-level explainer video and read the full paper here: t.co/YKJlabr3yb

https://www.nature.com/articles/s41562-025-02250-1

t.co

UCSF Neurosurgery@neurosurgucsf.bsky.social · last yr.

A new @nathumbehav.nature.com study from @changlabucsf.bsky.social identifies a key role for the middle precentral gyrus in coordinating the muscle movements required to speak, challenging the longstanding view that Broca's area controls this process: www.nature.com/articles/s41... 🧠📈 🧪