@Stanford_EE PhD Candidate | Digital Biomarkers x AI x NeuroTech Digital Health | Prev. Amazon, Meta, NASA JPL
Joined April 2012
- Tweets15.3K
- Following2.1K
- Followers1.2K
- Likes38.2K
Pinned Tweet
Your phone or smartwatch may detect Parkinson’s or Alzheimer’s years before your doctor does.
Our new @NatRevBioeng paper explains how digital biomarkers from everyday devices could transform brain health. 🧵
nature.com/articles/s44222-0…
Favour Nerrise 🇨🇲 retweeted
1/ Can AI help doctors make more informed decisions based on patient activity and behavior over the course of a hospital stay?
Today we introduce TRACER: a training-free multimodal harness that enables LLMs and VLMs to track patient activity using bedside video and health records.
Blogpost: ai.stanford.edu/blog/tracer/
Paper: arxiv.org/abs/2610.21266
Favour Nerrise 🇨🇲 retweeted
LLMs have tokens. Images have patches. What should the brain have? 🤔
HBAR, our hierarchical tokenizer for fMRI, was just accepted to NeurIPS 2026! 🎉
It compresses fMRI ~415× while preserving structure from voxels → parcels → functional networks.
🙌🏿 Looks I picked the right dissertation topic.
Loving all these Google Research Health contributions.
Finding clinical signals in large-scale health sensing data streams is quite challenging. We introduce a biomarker discovery framework that pairs hypothesis generation with adversarial validation to discover rigorous digital biomarkers alongside human experts. Read more: goo.gle/4gavroG
ALT Overview of the Biomarker Discovery Framework. (a) The system ingests time series data from consumer wearables and clinical labs. (b) A closed-loop architecture orchestrates six phases mirroring the human biomarker prioritization lifecycle. (c) An Orchestrator agent decomposes natural-language research directives into execution plans.
Favour Nerrise 🇨🇲 retweeted
Curriculum learning changes the data. Progressive stacking changes the model. Human development changes both at once.
What happens when language model pretraining does the same?
We explore this in Curriculum-Guided Layer Scaling (CGLS) 🧵
Favour Nerrise 🇨🇲 retweeted
The QuantiPhy Challenge is now officially open!
Register your team at: quantiphy.stanford.edu/compe…
Submit your results to win amazing prizes!!!
Thrilled to announce the 🏎️QuantiPhy Challenge🏃 to appear in #NeurIPS2026 Competition Track!
Read more at: quantiphy.stanford.edu/compe…
We host this competition to bring together attention from two important communities: VLMs and physics reasoning. How numerically accurate can your model estimate size/velocity/acceleration from video? Submit your results to the Quantiphy Challenge!!
P.S. We are seeking sponsors to prepare exciting prizes for winners! Please reach out for sponsors that are open to collaborate :)
Favour Nerrise 🇨🇲 retweeted
I am thrilled to share that UC Berkeley and UCSF have launched a joint initiative in Computational Biomedicine!
cdss.berkeley.edu/news/uc-be…
We will soon be recruiting new faculty and postdoctoral fellows. Please repost to help spread the word.
Favour Nerrise 🇨🇲 retweeted
Thrilled to share that our paper on AMIE—our conversational medical AI—is now published in @Nature. We wanted to tackle one of the most challenging areas in clinical AI: management reasoning over multiple patient visits.
nature.com/articles/s41586-0…
Favour Nerrise 🇨🇲 retweeted
🚨 New in Nature Medicine 🚨
Difficulty walking is one of the most disabling symptoms of Parkinson's disease—and one of the hardest to treat.
Today we're excited to share our new study showing that deep brain stimulation (DBS) can be synchronized to each step a person takes.
Favour Nerrise 🇨🇲 retweeted
The AI Startups in Africa dataset has been accepted to the Deep Learning Indaba 2026 Dataset Showcase! @DeepIndaba
This is the first conference the dataset will be formally presented at, and I anticipate great conversations.
doi.org/10.7910/DVN/Z0PKGO
Excited to be presenting our #CVPR2026 CV4Clinic workshop paper TODAY!✨
🧠GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
📍Poster 284 at 2:40 PM in Exhibit Hall A
📃: arxiv.org/abs/2605.01829
💻: github.com/favour-nerrise/Ge…
6/ ⚠️Another problem is age confounding in Alzheimer’s, where many features look disease-related even when they’re not.
✅ GeoSAE annotates features using age-adjusted clinical associations, & checks whether features relate to AD, sex, genetics, comorbidities, aging, etc.
7/ Across ~13k 3D brain MRI scans from ADNI and AIBL, GeoSAE finds a compact set of interpretable features that predicts MCI-to-AD conversion and replicates across cohorts.
🫂 Huge thanks to my amazing collaborators Lucy Yin, Mohammad H. Abbasi, Kilian M. Pohl, and @eadeli!
2/ Brain MRI foundation models can learn rich representations of anatomy, but it's still hard to know what clinical signals they are actually using.
For Alzheimer’s disease, this is especially important because age, brain structure, and disease progression are deeply linked.
Favour Nerrise 🇨🇲 retweeted
New online! Motor neuron disease in Africa: a critical appraisal of the literature dlvr.it/TSkDg5
Incredible contribution, congrats 🔥@keshigeyan @KyleSargentAI !!
1/ Introducing GPIC: a Giant Permissive Image Corpus and benchmark for visual generation!
🚀100M VLM-captioned image-text pairs for training
📊1M image-text pairs for benchmarking
🖼️~28 trillion pixels
🤗Centrally Hosted
✅Fully permissive for research + commercial use
Dataset, benchmark and models🧵👇
Co-led with @KyleSargentAI
