Principal ML Scientist at @Genentech @PrescientDesign. Bayesian optimization, Bayesian inference.
San Francisco Bay Area
Joined January 2014
- Tweets509
- Following1.3K
- Followers1.2K
- Likes1.6K
Ji Won Park retweeted
GuideLoom is live! Open-source tooling for training interpretable LLMs at scale. Try it out and let us know what you build.
Big milestone for @guidelabsai and the crew behind it. Huge credit to @andreas_madsen for turning an obstacle into a tool the broader research community can build on.
It’s live: the first open-sourced dataloader for training interpretable language models at scale, GuideLoom.
We’ve been using it to train models ranging from 100M params → 32B params, and now it’s yours.
GuideLoom stores your data (as documents, token streams, or token streams with annotations on spans of tokens) + during training, a PyTorch DataLoader shuffles across the entire dataset, lets every GPU read its own samples in parallel, and resumes from the exact batch after a restart.
pip install guideloom[torch]
Congrats to the Ortet team 🥳
We’re excited to announce Ortet, a frontier AI lab for health.
A fundamental gap in care today is that the industry and its scientific tools focus on discovering what works at the population level, while it is individual patients we must focus on to deliver the best care. Individualized care requires a broad view of the patient, the care they receive, and the system around them. Yet the information needed for such a view remains fragmented.
At Ortet, our goal is to create continuously improving intelligence for every patient: the Ortet Health Model, bringing together biological, clinical, and operational dimensions to better predict what happens next and which actions are most likely to lead to better outcomes. To deliver it, we are creating frontier AI from the ground up—across compute, data infrastructure, and models—and building and operating at every layer of AI.
We are scientists and engineers behind foundational AI advances, including the attention mechanism, GRU, and neural text-to-image generation. Across the team, our work spans frontier AI research, health, life sciences, and large-scale data and compute infrastructure—from building AI for lab-in-the-loop molecular design and co-founding Prescient Design to establishing Genentech’s frontier research team and building the largest GPU cluster in life sciences.
We imagine a future where everyone has access to affordable, precise, and better care.
If you want to help us build that future, join us: ortet.ai
Ji Won Park retweeted
I’m very excited to announce that I'm founding @OrtetAI with my amazing co-founders @kchonyc, @keunwoochoi, @elmanmansimov
@causalclaudia and Jeff Hammerbacher.
At Genentech, I saw how a great team can build AI to make a difference for molecular design. With Ortet, I believe we can create intelligence that will improve care for all.
If you’re interested in AI and health please reach out.
See ortet.ai/ for more.
Ji Won Park retweeted
i'm co-founding @OrtetAI to create continuously improving intelligence for every patient.
we're hiring! please join the Ortet crews - @kchonyc @HenriDwyer @elmanmansimov @causalclaudia - more on ortet.ai
We’re excited to announce Ortet, a frontier AI lab for health.
A fundamental gap in care today is that the industry and its scientific tools focus on discovering what works at the population level, while it is individual patients we must focus on to deliver the best care. Individualized care requires a broad view of the patient, the care they receive, and the system around them. Yet the information needed for such a view remains fragmented.
At Ortet, our goal is to create continuously improving intelligence for every patient: the Ortet Health Model, bringing together biological, clinical, and operational dimensions to better predict what happens next and which actions are most likely to lead to better outcomes. To deliver it, we are creating frontier AI from the ground up—across compute, data infrastructure, and models—and building and operating at every layer of AI.
We are scientists and engineers behind foundational AI advances, including the attention mechanism, GRU, and neural text-to-image generation. Across the team, our work spans frontier AI research, health, life sciences, and large-scale data and compute infrastructure—from building AI for lab-in-the-loop molecular design and co-founding Prescient Design to establishing Genentech’s frontier research team and building the largest GPU cluster in life sciences.
We imagine a future where everyone has access to affordable, precise, and better care.
If you want to help us build that future, join us: ortet.ai
Ji Won Park retweeted
i was diagnosed with thyroid cancer many years ago purely by chance, because i had to get blood work for my US green card application (thank you, USCIS!). i was in my mid-30’s and was reasonably healthy (or so i believed.) this was shocking and totally unpredictable news to me. thanks to the amazing team of clinicians at NYU Langone, i successfully went through a total thyroidectomy followed by radioactive iodine therapy. but, it was truly the most uncertain and confusing period of my life.
this is when i first realized that no one can opt out of healthcare. being sick isn’t what you choose to or choose not to. it is something that unpredictably happens to all of us at some point for one reason or another. this is why it is a healthcare system that we collectively build and use to support each other at the society level. because it must support everyone, the complexity of creating, maintaining and improving this system is a Herculean effort that calls for all the help in the world.
today, i am announcing @OrtetAI together with my dear co-founders, @keunwoochoi, @HenriDwyer, @elmanmansimov, @causalclaudia and Jeff, to lend our support to improving the health of each and every one of us. Ortet’s goal is to create a technological foundation that will enable health systems to deliver predictably better care to each and every patient. this will only be possible by working closely with all stakeholders in the broader ecosystem, which is enabled in part by Ortet’s close partnership with Thoreau.
Ortet is taking the very first step of a long journey ahead, and at the end of this journey, i strongly believe we would be able to say that Ortet had contributed to building better, more predictable healthcare and thus to improving health of each and every one of us.
see ortet.ai/ for more!
Material from the workshop I taught in July at Seoul National University on multi-objective Bayesian optimization
jiwoncpark.github.io/talks/2…
Ji Won Park retweeted
UPDATE: Steerling-8b has broken through the assumption that larger models + more data are harder to interpret →
Interpretability can be forecasted before an expensive run, and we can estimate ROI from params and data.
Instead of a black box you have to reverse-engineer afterward, Steerling-8b’s concept attribution has shown:
- the larger the interpretable model, the more disentangled its representations
- training more data makes the model’s representations more human-aligned
Ji Won Park retweeted
Excellent talk by @thjashin:
- What separates autoregression and diffusion?
- Bridging the gap between continuous and masked discrete diffusion via loss reweighting
- Insertion-based sequence generation
Very clear and easy to follow! (via @mblondel_ml)
youtube.com/watch?v=kMimQxIJ…
Ji Won Park retweeted
the era of computational math and stat is here: a proof within computational budget and constraints by search rather than a proof under strong assumptions by derivation.
along this line of progress, @luciusbynum, rajesh ranganath and yours truly put forward computational identifiability.
the link to arxiv below.
Ji Won Park retweeted
Statistics as a field has not historically oriented itself around formalized open problems. Part of the reason is that the hardest problems in the field are ones of formalizing what the problem even is. Once you formalize a problem, much of the work may be done. Of course, there are counter examples, but, if I were to cast statistics as an AI problem, I think the bulk of (impactful) statistics is closer to auto-formalization than to theorem proving.
Ji Won Park retweeted
Grateful to be at ICML in Seoul 🇰🇷 this week! Excited to chat with people about agent control and monitoring; statistical uncertainty quantification; safe, regulatable, & trustworthy AI, etc. DM if you’d like to chat!
Or, find me at one of the sessions below in thread (1/6):
Can we ensure AI agents respect our safety constraints, even as they explore & improve?
- Medical LLMs that are helpful, & avoid false claims?
- Bioscience agents that generate effective molecule designs, & ensure they’re safe?
📄🧵w/ @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
Excited to share “Conformal Policy Control” ⬇️
1/12
Ji Won Park retweeted
Join us for an exciting workshop on AI for Drug Discovery & Development in NYC🍎!
We have a superstar lineup of speakers, which could include YOU! Submit an abstract by 7/17!
Hosted by NYU & the Global Frontier AI Lab @nyuniversity @kchonyc
Sponsored by @genentech @jiwoncpark
Excited to announce the 2026 Northeast AI for Drug Discovery & Development Workshop, sponsored by Genentech!
📍 NYU, Brooklyn, NY
📅 Aug 3, 2026
🌐 ai4d3.github.io
Join us for talks and discussions on AI for drug discovery and development, lab automation, and AI agents.
Ji Won Park retweeted
We can now edit a cell that won't respond to a drug into one that does, in silico.
With the BRAID team at @genentech, we built scCBGM: an interpretable #AI model that extracts the mechanism behind a cell's response, then lets you act on it. 🧵
Ji Won Park retweeted
We're open-sourcing pathmc!
Structural causal models + #Bayesian estimation in one package. Define assumptions once, then estimate effects, test identifiability, run interventions, and perform sensitivity analysis.
GitHub: dub.sh/2hG8kAu
Docs: dub.sh/rvUHI78
Ji Won Park retweeted
It took us a minute, but the technical report for Steerling is finally out!
It's a bit long, 116 pages of every decision we made (and every mistake too 🤦♀️). We tried to document everything so the community doesn't have to rediscover it the hard way.
This is the paper we wish existed when we started.
guidelabs.ai/papers/scaling-…
Ji Won Park retweeted
TwinWeaver is accepted to ICML 2026.
model:
- LLM-based pan-cancer digital twin
data:
- 93k oncology patients, 20 cancer types
- textifying everything - labs, biomarkers, genetics, therapies
and:
- beats specialized time-series + EHR foundation models
ALT twinweaver framework - a general framework for LLM-based patient digital twins from longitudinal, multi-modal data
Ji Won Park retweeted
Our interpretability seminar today (22/04) features @asalam_91 from @guidelabsai presenting the largest interpretable model in the world!
🗓️ Topic
Steerling-8B: Inherently Interpretable Language Model
Tune in live at 5:30 CEST / 8:30 PST: 📷youtube.com/@InterpretableDe…
Ji Won Park retweeted
Can we ensure AI agents respect our safety constraints, even as they explore & improve?
- Medical LLMs that are helpful, & avoid false claims?
- Bioscience agents that generate effective molecule designs, & ensure they’re safe?
📄🧵w/ @samuel_stanton_ @clara_fannjiang @jiwoncpark @kchonyc @anqi_liu33 @suchisaria
Excited to share “Conformal Policy Control” ⬇️
1/12
Ji Won Park retweeted
if you speak Korean but are not a Korean and are interested in working as a researcher/research analyst at the Korean Mission to the United Nations in NYC, consider this position: un.mofa.go.kr/un-ko/brd/m_24…
Ji Won Park retweeted
congrats to anthropic for snapping up coefficient bio!
what a great beginning of the great prescient design alumni network, @nc_frey @samuel_stanton_ jesse!
stay tuned to hear more from other entrepreneurial alumni, such as @juliusadml and @asalam_91 of Gauss Lab.