Minh Nguyen

Data Scientist -
PhD @StanfordDBDS, M.A @UCBerkeley Biostats, RN @UCSFHealth

[Abridge @AbridgeHQ]

The energy is flowing sky high this morning as the lines begin for our hackathon! Can’t wait to see what these builders create…

Any thoughts on what we expect today?

@AnthropicAI @lightspeedvp @cerebral_valley

#AbridgeBuildDay

[Jonathan H Chen MD PhD @jonc101x]

Congrats to @minhnsf on completing her @StanfordDBDS PhD. Looking for an experienced nurse, statistician, data scientist, and more? She's demonstrated the tenacity to push through advances in all of the above.

[Jonathan H Chen MD PhD @jonc101x]

Machine learning, data, and statistics will get you so far. Eventually you'll need domain expertise to dive in to unpack what it all means in context. @minhnsf Tiffany Eulalio @benmarafino @RoseLikeTheFlwr @BaiocchiMike
https://t.co/ov1hshC71N

[Minh Nguyen @minhnsf]

@TiffanyEulalio @benmarafino @RoseLikeTheFlwr @jonc101x @BaiocchiMike
TDA is a follow-up of our previously published work https://t.co/OJk2Y0sAAL
with Conor Corbin, @gmachiraju, and Nicolai Ostberg

[Minh Nguyen @minhnsf]

Implementing ML models in clinical settings is limited & challenging. A feedback loop + a meaningful collaboration between researchers and domain experts are important. We proposed TDA, a statistical investigation framework to assess interesting phenomenons from ML outputs

[StanfordDBDS @StanfordDBDS]

DBDS' Minh Nguyen, Tiffany Eulalio & Ben Marafino published "Thick Data Analytics (TDA): An Iterative and Inductive Framework for Algorithmic Improvement" in The American Statistician
Read it here: https://t.co/HnA4MDtrvh

[Minh Nguyen @minhnsf]

Awesome work! 🫡‼️🙌🎉@gmachiraju and @awfderry

[Gautam "Machi" Machiraju @gmachiraju]

Given up on feature attribution?

📣 Thrilled to share *prospector heads* (aka “prospectors'') ⛏️ — a simple attribution method built for foundation models (FMs) & high-dimensional data. Prospectors are modality-generalizable, time-efficient, & excel in few-shot settings ✨

🧵👇

[Minh Nguyen @minhnsf]

@AkliluJosiah2 @NEJM_AI Josiah and Min Woo, you 2 are rocking this! congrats 😍

[Minh Nguyen @minhnsf]

@hapyresearchers Maybe not so much about being right/wrong but if your work is useful or not

[Minh Nguyen @minhnsf]

@NEJM_AI @oziadias 🙌

[Minh Nguyen @minhnsf]

@mdredze "wrong titles only" 😂

[Minh Nguyen @minhnsf]

I didn't get it at first. LMAO 😂

[Christopher Potts @ChrisGPotts]

According to the first sentence of 100% of the papers I have reviewed this year, large language models have achieved amazing success in recent years. Perhaps we could settle on the abbreviation "Language Models Are Outstanding", so papers could begin "LMAO, but …" to save space.

[Minh Nguyen @minhnsf]

@omarsar0 How does this compare to Gihub copilot?

[Minh Nguyen @minhnsf]

@linylinx That's insane 😔

[Minh Nguyen @minhnsf]

@PHDcomics 😅also, everyone else is starving like the undergrad

[Minh Nguyen @minhnsf]

What makes a good conference great is the people you meet and spend time with. So much to learn. Thank you and I will always be a fan of your works. Cheers, until next time! 😍 #ACIC2023

[Minh Nguyen @minhnsf]

@laura_tastic @guido_imbens @mats_julius Thank you! It was nice to finally meet you in person

[Minh Nguyen @minhnsf]

The amazing Lina on an important topic of research #ACIC2023

[Minh Nguyen @minhnsf]

Last day #ACIC2023:
1. A great session on assessing bias and optimizing treatments @guido_imbens, @mats_julius, and @ V. Rivera-Burgos & T. Leavitt
2. My favorite word is "homoskedasticity"
3. My poster was an honorable mention for the SCI's Tom Ten Have award, almost a winner!

[Minh Nguyen @minhnsf]

One of my favorite talks at #ACIC2023