Rohit Vashisht
@rohitv.bsky.social
Evolutionary Biology | Healthcare Analytics | Carnatic Music @UCSF | past @Stanford
https://rohit43.github.io/
https://rohit43.github.io/
Pinned
Rohit Vashisht
@rohitv.bsky.social
· Nov 24
Above all, try!
Reposted by Rohit Vashisht
“It is simpler to do erroneous things.” - @f2harrell.bsky.social
H/t @phdemetri.bsky.social
stats.stackexchange.com/questions/67...
H/t @phdemetri.bsky.social
stats.stackexchange.com/questions/67...
Why include unadjusted estimates in a study when reporting adjusted estimates?
Upon reading "The Strengthening the Reporting of Observational Studies in Epidemiology " or STROBE guidelines, one will find advice to
(a) Give unadjusted estimates and, if applicable,
stats.stackexchange.com
September 29, 2025 at 4:21 AM
“It is simpler to do erroneous things.” - @f2harrell.bsky.social
H/t @phdemetri.bsky.social
stats.stackexchange.com/questions/67...
H/t @phdemetri.bsky.social
stats.stackexchange.com/questions/67...
Reposted by Rohit Vashisht
One of the fun things about launching @timead.bsky.social is the amazing early career folks. We started a "scientist spotlight" website section. The 3 posted are just our first few - really gratifying to see the work of Master's & PhD students, and post-docs -more spotlights coming!
bit.ly/3VCa84g
bit.ly/3VCa84g
September 26, 2025 at 1:28 PM
One of the fun things about launching @timead.bsky.social is the amazing early career folks. We started a "scientist spotlight" website section. The 3 posted are just our first few - really gratifying to see the work of Master's & PhD students, and post-docs -more spotlights coming!
bit.ly/3VCa84g
bit.ly/3VCa84g
September 26, 2025 at 6:24 PM
Reposted by Rohit Vashisht
I wrote a LinkedIn post on advice for incoming Master's students in public health and epidemiology. tl;dr: do hard things, get help when needed, make friends and thank people, and have fun - it's amazing. #EpiSky #DataSciSky #PublicHealth #GradSchool
Full article: bit.ly/4neVYlE
Full article: bit.ly/4neVYlE
September 23, 2025 at 12:38 AM
I wrote a LinkedIn post on advice for incoming Master's students in public health and epidemiology. tl;dr: do hard things, get help when needed, make friends and thank people, and have fun - it's amazing. #EpiSky #DataSciSky #PublicHealth #GradSchool
Full article: bit.ly/4neVYlE
Full article: bit.ly/4neVYlE
Tired: Global interpreter lock for data heavy parallel processing in Python
Wired: Reading data in 1GB chunks and processing sequentially
Wired: Reading data in 1GB chunks and processing sequentially
September 20, 2025 at 5:07 PM
Tired: Global interpreter lock for data heavy parallel processing in Python
Wired: Reading data in 1GB chunks and processing sequentially
Wired: Reading data in 1GB chunks and processing sequentially
September 19, 2025 at 1:32 AM
Reposted by Rohit Vashisht
We love to see JCHI's @kdpsingh.bsky.social, @ucsdhealth.bsky.social named one of 24 new ACMI Fellows!
His leadership in health AI, model governance & informatics policy is reshaping how AI is used responsibly in care.
Read more⤵️
amia.org/news-publica...
His leadership in health AI, model governance & informatics policy is reshaping how AI is used responsibly in care.
Read more⤵️
amia.org/news-publica...
September 17, 2025 at 9:33 PM
We love to see JCHI's @kdpsingh.bsky.social, @ucsdhealth.bsky.social named one of 24 new ACMI Fellows!
His leadership in health AI, model governance & informatics policy is reshaping how AI is used responsibly in care.
Read more⤵️
amia.org/news-publica...
His leadership in health AI, model governance & informatics policy is reshaping how AI is used responsibly in care.
Read more⤵️
amia.org/news-publica...
From Clinician to Chief Health AI Officer: A Conversation with @kdpsingh.bsky.social www.podbean.com/ew/pb-9t5e4-...
For clinicians, Singh’s story is a reminder that the best AI is guided by patient care, deep expertise, and humility about the limits of technology.
Inspiring!
For clinicians, Singh’s story is a reminder that the best AI is guided by patient care, deep expertise, and humility about the limits of technology.
Inspiring!
From Clinician to Chief Health AI Officer: A Conversation with Dr. Karandeep Singh | NEJM AI Grand Rounds
Dr. Karandeep Singh brings two worlds together: programming and medicine. In this conversation, he explains how early experiments with code led him to biomedical informatics, why gaps between paper pe...
www.podbean.com
September 17, 2025 at 2:50 PM
From Clinician to Chief Health AI Officer: A Conversation with @kdpsingh.bsky.social www.podbean.com/ew/pb-9t5e4-...
For clinicians, Singh’s story is a reminder that the best AI is guided by patient care, deep expertise, and humility about the limits of technology.
Inspiring!
For clinicians, Singh’s story is a reminder that the best AI is guided by patient care, deep expertise, and humility about the limits of technology.
Inspiring!
Late night LLM training thoughts:
I’m increasingly appreciating APEs over other position embedding. Their simplicity makes them easy to implement and efficient in distributed training setups. APEs could also provide a stable foundation for enhancing the consistency of LLMs.
I’m increasingly appreciating APEs over other position embedding. Their simplicity makes them easy to implement and efficient in distributed training setups. APEs could also provide a stable foundation for enhancing the consistency of LLMs.
September 14, 2025 at 7:02 AM
Late night LLM training thoughts:
I’m increasingly appreciating APEs over other position embedding. Their simplicity makes them easy to implement and efficient in distributed training setups. APEs could also provide a stable foundation for enhancing the consistency of LLMs.
I’m increasingly appreciating APEs over other position embedding. Their simplicity makes them easy to implement and efficient in distributed training setups. APEs could also provide a stable foundation for enhancing the consistency of LLMs.
qwen is good, like really good!
September 12, 2025 at 9:03 PM
qwen is good, like really good!
Reposted by Rohit Vashisht
Statistician: What is zero-shot learning?
ML researcher: It’s when you don’t train your model, you just use it.
Stats: So you just take a shot?
ML: Exactly.
Stats: One shot…
ML: Exactly.
Stats: …
ML: Makes sense tho. Think of it like Python list indexing, where the first shot is the zeroeth.
ML researcher: It’s when you don’t train your model, you just use it.
Stats: So you just take a shot?
ML: Exactly.
Stats: One shot…
ML: Exactly.
Stats: …
ML: Makes sense tho. Think of it like Python list indexing, where the first shot is the zeroeth.
September 9, 2025 at 5:52 PM
Statistician: What is zero-shot learning?
ML researcher: It’s when you don’t train your model, you just use it.
Stats: So you just take a shot?
ML: Exactly.
Stats: One shot…
ML: Exactly.
Stats: …
ML: Makes sense tho. Think of it like Python list indexing, where the first shot is the zeroeth.
ML researcher: It’s when you don’t train your model, you just use it.
Stats: So you just take a shot?
ML: Exactly.
Stats: One shot…
ML: Exactly.
Stats: …
ML: Makes sense tho. Think of it like Python list indexing, where the first shot is the zeroeth.
Manuscript review requests are like poking one bee and getting the whole dang hive buzzing after you!
Say yes to one, and suddenly you’re swarmed with a zillion more “review this, please!” emails.
Say yes to one, and suddenly you’re swarmed with a zillion more “review this, please!” emails.
September 9, 2025 at 2:14 AM
Manuscript review requests are like poking one bee and getting the whole dang hive buzzing after you!
Say yes to one, and suddenly you’re swarmed with a zillion more “review this, please!” emails.
Say yes to one, and suddenly you’re swarmed with a zillion more “review this, please!” emails.
Reposted by Rohit Vashisht
Mother: I have twins.
Doctor: Oh, so they were born on the same day?
Mother: No, they were born with the same propensity score.
Doctor: Oh, so they were born on the same day?
Mother: No, they were born with the same propensity score.
September 5, 2025 at 7:49 PM
Mother: I have twins.
Doctor: Oh, so they were born on the same day?
Mother: No, they were born with the same propensity score.
Doctor: Oh, so they were born on the same day?
Mother: No, they were born with the same propensity score.
Reposted by Rohit Vashisht
Tired: Adjusting for covariates
Wired: “Building a digital twin”
Wired: “Building a digital twin”
September 5, 2025 at 3:17 PM
Tired: Adjusting for covariates
Wired: “Building a digital twin”
Wired: “Building a digital twin”
If you understand the nullspace, you understand the matrix!
— Gilbert Strang
— Gilbert Strang
August 31, 2025 at 1:05 AM
If you understand the nullspace, you understand the matrix!
— Gilbert Strang
— Gilbert Strang
Reposted by Rohit Vashisht
“Our model is probably in our view the best model for this task and the fastest and second cheapest but not the best performing but the benchmarks don’t reflect the nuances of real-world use” is a whole lot of words to say that it’s not SOTA.
August 30, 2025 at 3:21 AM
“Our model is probably in our view the best model for this task and the fastest and second cheapest but not the best performing but the benchmarks don’t reflect the nuances of real-world use” is a whole lot of words to say that it’s not SOTA.
Tired: Long context length
Wired: No context length
Wired: No context length
August 28, 2025 at 7:16 PM
Tired: Long context length
Wired: No context length
Wired: No context length
The more I learn about @duckdb.org the more amazed I get, and more I realize how much I don’t really know, and a long way to go!
August 27, 2025 at 4:16 AM
The more I learn about @duckdb.org the more amazed I get, and more I realize how much I don’t really know, and a long way to go!
Reposted by Rohit Vashisht
Streamline data app development in Positron with the App Preview feature. 🪟
No more context-switching! Now you can run & debug your #RStats and #Python data apps (Shiny, Streamlit, Dash, etc.) right inside Positron's integrated Viewer pane.
Learn more: positron.posit.co/develop-data...
No more context-switching! Now you can run & debug your #RStats and #Python data apps (Shiny, Streamlit, Dash, etc.) right inside Positron's integrated Viewer pane.
Learn more: positron.posit.co/develop-data...
August 25, 2025 at 2:21 PM
Streamline data app development in Positron with the App Preview feature. 🪟
No more context-switching! Now you can run & debug your #RStats and #Python data apps (Shiny, Streamlit, Dash, etc.) right inside Positron's integrated Viewer pane.
Learn more: positron.posit.co/develop-data...
No more context-switching! Now you can run & debug your #RStats and #Python data apps (Shiny, Streamlit, Dash, etc.) right inside Positron's integrated Viewer pane.
Learn more: positron.posit.co/develop-data...
Is outlook down? Or just me!
August 18, 2025 at 1:12 AM
Is outlook down? Or just me!
Reposted by Rohit Vashisht
At this point, the statisticians might even settle for a physician doing the statistics rather than this nonsense.
August 12, 2025 at 12:53 AM
At this point, the statisticians might even settle for a physician doing the statistics rather than this nonsense.
Positron’s integrated color picker is super handy for tweaking colors directly in your code!
August 10, 2025 at 6:48 PM
Positron’s integrated color picker is super handy for tweaking colors directly in your code!
Reposted by Rohit Vashisht
Data to Decisions: Engineering the Foundations for Target Trial Emulation and Causal Inference in Medicine Across @uofcahealth.bsky.social
Excited for this talk at UCSF-Epibiostat. I will discuss our ongoing efforts in harnessing large-scale RWD for post-market monitoring of therapeutic.
Excited for this talk at UCSF-Epibiostat. I will discuss our ongoing efforts in harnessing large-scale RWD for post-market monitoring of therapeutic.
August 3, 2025 at 6:12 AM
Data to Decisions: Engineering the Foundations for Target Trial Emulation and Causal Inference in Medicine Across @uofcahealth.bsky.social
Excited for this talk at UCSF-Epibiostat. I will discuss our ongoing efforts in harnessing large-scale RWD for post-market monitoring of therapeutic.
Excited for this talk at UCSF-Epibiostat. I will discuss our ongoing efforts in harnessing large-scale RWD for post-market monitoring of therapeutic.