Austin Tripp
@austinjtripp.bsky.social
(ML ∪ Bayesian optimization ∪ active learning) ∩ (drug discovery)
Researcher @valenceai.bsky.social
Details: austintripp.ca
Researcher @valenceai.bsky.social
Details: austintripp.ca
NeurIPS reviews are due in 1 week 😱
If it's your first time reviewing (or if you don't feel totally confident about accept/reject), I recently wrote a blog post where I explain how *I* approach reviewing. Essentially:
accept = correct AND (result OR idea) [...]
If it's your first time reviewing (or if you don't feel totally confident about accept/reject), I recently wrote a blog post where I explain how *I* approach reviewing. Essentially:
accept = correct AND (result OR idea) [...]
June 25, 2025 at 8:14 AM
NeurIPS reviews are due in 1 week 😱
If it's your first time reviewing (or if you don't feel totally confident about accept/reject), I recently wrote a blog post where I explain how *I* approach reviewing. Essentially:
accept = correct AND (result OR idea) [...]
If it's your first time reviewing (or if you don't feel totally confident about accept/reject), I recently wrote a blog post where I explain how *I* approach reviewing. Essentially:
accept = correct AND (result OR idea) [...]
Reposted by Austin Tripp
1/ At Valence Labs, @recursionpharma.bsky.social's AI research engine, we’re focused on advancing drug discovery outcomes through cutting-edge computational methods
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
May 20, 2025 at 3:55 PM
1/ At Valence Labs, @recursionpharma.bsky.social's AI research engine, we’re focused on advancing drug discovery outcomes through cutting-edge computational methods
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
For anybody working on multi-objective optimization: I recently did a deep-dive on Chebyshev scalarization and wrote a blog post. Key findings:
1. Unlike linear scalarization, varying the weights of Chebyshev scalarization will find *all* points on the Pareto front (not just the convex part)
...
1. Unlike linear scalarization, varying the weights of Chebyshev scalarization will find *all* points on the Pareto front (not just the convex part)
...
May 16, 2025 at 11:07 AM
For anybody working on multi-objective optimization: I recently did a deep-dive on Chebyshev scalarization and wrote a blog post. Key findings:
1. Unlike linear scalarization, varying the weights of Chebyshev scalarization will find *all* points on the Pareto front (not just the convex part)
...
1. Unlike linear scalarization, varying the weights of Chebyshev scalarization will find *all* points on the Pareto front (not just the convex part)
...
Reposted by Austin Tripp
(1/3)The poster submission deadline for MoML 2025 has been extended to May 20th, 2025.
Don’t miss an opportunity to share your work at this years conference.
Submit here: portal.ml4dd.com/moml-2025-po...
Don’t miss an opportunity to share your work at this years conference.
Submit here: portal.ml4dd.com/moml-2025-po...
May 13, 2025 at 1:19 PM
(1/3)The poster submission deadline for MoML 2025 has been extended to May 20th, 2025.
Don’t miss an opportunity to share your work at this years conference.
Submit here: portal.ml4dd.com/moml-2025-po...
Don’t miss an opportunity to share your work at this years conference.
Submit here: portal.ml4dd.com/moml-2025-po...
Really interesting essay- disagreements about AI existential risk might *really* be disagreements about dual-use nature of future technologies (since this is the vector people think AI could cause extinction).
New essay exploring why experts so strongly disagree about existential risk from ASI, and why focusing on alignment as the primary goal may be a fundamental mistake
michaelnotebook.com/xriskbrief/i...
michaelnotebook.com/xriskbrief/i...
April 24, 2025 at 11:30 AM
Really interesting essay- disagreements about AI existential risk might *really* be disagreements about dual-use nature of future technologies (since this is the vector people think AI could cause extinction).
Claude and Gemini do a pretty good job at coding some niche python packages from just a prompt. Some editing required, but if you haven't tried it yet then I highly recommend!
www.austintripp.ca/blog/2025-04...
www.austintripp.ca/blog/2025-04...
Coding python packages with AI
I tried using some new LLM tools to code 2 entire python packages (instead of
editing a handful of lines at a time, which is what I did previously). It went
well! These tools are not perfect, but they
www.austintripp.ca
April 14, 2025 at 8:38 AM
Claude and Gemini do a pretty good job at coding some niche python packages from just a prompt. Some editing required, but if you haven't tried it yet then I highly recommend!
www.austintripp.ca/blog/2025-04...
www.austintripp.ca/blog/2025-04...
Can anybody explain to me why so many ML papers study "offline model-based optimization"? This is essentially "1-shot optimization".
My main concern is "are there 1-shot optimization problems in real life"? Papers mention "drug discovery (DD)" as an example, but 1-shot DD never happens, no? 😂
My main concern is "are there 1-shot optimization problems in real life"? Papers mention "drug discovery (DD)" as an example, but 1-shot DD never happens, no? 😂
February 14, 2025 at 10:08 AM
Can anybody explain to me why so many ML papers study "offline model-based optimization"? This is essentially "1-shot optimization".
My main concern is "are there 1-shot optimization problems in real life"? Papers mention "drug discovery (DD)" as an example, but 1-shot DD never happens, no? 😂
My main concern is "are there 1-shot optimization problems in real life"? Papers mention "drug discovery (DD)" as an example, but 1-shot DD never happens, no? 😂
Reposted by Austin Tripp
People who are masking are smart for two reasons:
1. They do not want to get brain damage
2. They are not getting brain damage
1. They do not want to get brain damage
2. They are not getting brain damage
February 7, 2025 at 7:38 AM
People who are masking are smart for two reasons:
1. They do not want to get brain damage
2. They are not getting brain damage
1. They do not want to get brain damage
2. They are not getting brain damage
My bid screen for ICML position papers is basically:
- "Position: ML conference peer review is sh*t"
- "Position: Let's abolish conference reviewing"
- "Position: C'mon ML reviewers, surely we can do better than *this*"
Am I in a "review hate" echo chamber or is everybody else seeing this too? 😶
- "Position: ML conference peer review is sh*t"
- "Position: Let's abolish conference reviewing"
- "Position: C'mon ML reviewers, surely we can do better than *this*"
Am I in a "review hate" echo chamber or is everybody else seeing this too? 😶
January 31, 2025 at 9:26 AM
My bid screen for ICML position papers is basically:
- "Position: ML conference peer review is sh*t"
- "Position: Let's abolish conference reviewing"
- "Position: C'mon ML reviewers, surely we can do better than *this*"
Am I in a "review hate" echo chamber or is everybody else seeing this too? 😶
- "Position: ML conference peer review is sh*t"
- "Position: Let's abolish conference reviewing"
- "Position: C'mon ML reviewers, surely we can do better than *this*"
Am I in a "review hate" echo chamber or is everybody else seeing this too? 😶
Easy to get started on the antiviral challenge! I plan to submit some GP baselines from my PhD work (possibly with a collaborator).
It only takes a few lines of code to get started with the @asapdiscovery.bsky.social x @omsf.io antiviral challenge!
In this short tutorial, we’ll show you how easy it is to login, load the challenge data, train a simple baseline model, and submit your predictions 🧵
youtu.be/KBZJFA_arAg
In this short tutorial, we’ll show you how easy it is to login, load the challenge data, train a simple baseline model, and submit your predictions 🧵
youtu.be/KBZJFA_arAg
Tutorial: Getting Started with the Antiviral Challenge
YouTube video by PolarisHQ
youtu.be
January 26, 2025 at 9:25 PM
Easy to get started on the antiviral challenge! I plan to submit some GP baselines from my PhD work (possibly with a collaborator).
Reposted by Austin Tripp
🏁 The antiviral challenge is live! 🏁
Ready to test your skills on new data? Hosted in partnership with @asapdiscovery.bsky.social and @omsf.io, we've prepared detailed notebooks showcasing how to format your data and submit your solutions. 🧑💻
Ready to test your skills on new data? Hosted in partnership with @asapdiscovery.bsky.social and @omsf.io, we've prepared detailed notebooks showcasing how to format your data and submit your solutions. 🧑💻
January 14, 2025 at 2:31 PM
🏁 The antiviral challenge is live! 🏁
Ready to test your skills on new data? Hosted in partnership with @asapdiscovery.bsky.social and @omsf.io, we've prepared detailed notebooks showcasing how to format your data and submit your solutions. 🧑💻
Ready to test your skills on new data? Hosted in partnership with @asapdiscovery.bsky.social and @omsf.io, we've prepared detailed notebooks showcasing how to format your data and submit your solutions. 🧑💻
My PhD thesis is finally online. Thanks @cambridgemlg.bsky.social for a wonderful 4.5 years learning about probabilistic ML 😍
Code: github.com/austint/phd-...
Thesis DOI: doi.org/10.17863/CAM...
Code: github.com/austint/phd-...
Thesis DOI: doi.org/10.17863/CAM...
GitHub - AustinT/phd-thesis: LaTeX code for my PhD thesis (https://doi.org/10.17863/CAM.114023)
LaTeX code for my PhD thesis (https://doi.org/10.17863/CAM.114023) - AustinT/phd-thesis
github.com
January 13, 2025 at 8:43 AM
My PhD thesis is finally online. Thanks @cambridgemlg.bsky.social for a wonderful 4.5 years learning about probabilistic ML 😍
Code: github.com/austint/phd-...
Thesis DOI: doi.org/10.17863/CAM...
Code: github.com/austint/phd-...
Thesis DOI: doi.org/10.17863/CAM...
A common issue I see in ML, both from ML "experts" and "users", is overly optimistic assumptions.
"experts" (people designing algs) usually assume the data is very simple
"users" (people using algs) usually assume that algorithms are more robust than they really are
Conclusion: always be careful!
"experts" (people designing algs) usually assume the data is very simple
"users" (people using algs) usually assume that algorithms are more robust than they really are
Conclusion: always be careful!
January 10, 2025 at 9:46 AM
A common issue I see in ML, both from ML "experts" and "users", is overly optimistic assumptions.
"experts" (people designing algs) usually assume the data is very simple
"users" (people using algs) usually assume that algorithms are more robust than they really are
Conclusion: always be careful!
"experts" (people designing algs) usually assume the data is very simple
"users" (people using algs) usually assume that algorithms are more robust than they really are
Conclusion: always be careful!
Reposted by Austin Tripp
📊 Imagining the Future of ML Evaluation in Drug Discovery
Our recent paper discussed the limitations of static leaderboards—they never tell the full story. What if we had a better and easier way of evaluating methods?
A vision for the future, in the latest blog 🧵
polarishub.io/blog/imagini...
Our recent paper discussed the limitations of static leaderboards—they never tell the full story. What if we had a better and easier way of evaluating methods?
A vision for the future, in the latest blog 🧵
polarishub.io/blog/imagini...
December 18, 2024 at 5:19 PM
📊 Imagining the Future of ML Evaluation in Drug Discovery
Our recent paper discussed the limitations of static leaderboards—they never tell the full story. What if we had a better and easier way of evaluating methods?
A vision for the future, in the latest blog 🧵
polarishub.io/blog/imagini...
Our recent paper discussed the limitations of static leaderboards—they never tell the full story. What if we had a better and easier way of evaluating methods?
A vision for the future, in the latest blog 🧵
polarishub.io/blog/imagini...
Valence is a great place to work- come find me at NeurIPS today if you want to learn more!
Missed the event yesterday? Our team is still at NeurIPS today and throughout the workshops.
Come talk to us and learn more about open roles. We’re hiring for both full-time and internship positions: www.valencelabs.com/careers
Come talk to us and learn more about open roles. We’re hiring for both full-time and internship positions: www.valencelabs.com/careers
December 15, 2024 at 5:53 PM
Valence is a great place to work- come find me at NeurIPS today if you want to learn more!
This looks like a really cool competition for small molecule property prediction in both 3D and 2D- great opportunity to work with real data 🚀
🦠 We’re excited to announce our first competition in partnership with @asapdiscovery.bsky.social and @omsf.io!
Test your skills across three sub-challenges revolving around SARS-CoV-2 and MERS-CoV Mpro🧵
Full details: polarishub.io/competitions
Blog: polarishub.io/blog/antivir...
Test your skills across three sub-challenges revolving around SARS-CoV-2 and MERS-CoV Mpro🧵
Full details: polarishub.io/competitions
Blog: polarishub.io/blog/antivir...
December 6, 2024 at 7:41 PM
This looks like a really cool competition for small molecule property prediction in both 3D and 2D- great opportunity to work with real data 🚀
I'm attending NeurIPS next week- reach out if you want to meet for ☕️
I'm particularly interested in meeting:
1. PhD students interested in internships at Valence
2. people working on Bayesian optimization / active learning
3. anyone in tech-bio
4. early-career researchers
Details in 🧵 below
I'm particularly interested in meeting:
1. PhD students interested in internships at Valence
2. people working on Bayesian optimization / active learning
3. anyone in tech-bio
4. early-career researchers
Details in 🧵 below
December 3, 2024 at 12:20 PM
I'm attending NeurIPS next week- reach out if you want to meet for ☕️
I'm particularly interested in meeting:
1. PhD students interested in internships at Valence
2. people working on Bayesian optimization / active learning
3. anyone in tech-bio
4. early-career researchers
Details in 🧵 below
I'm particularly interested in meeting:
1. PhD students interested in internships at Valence
2. people working on Bayesian optimization / active learning
3. anyone in tech-bio
4. early-career researchers
Details in 🧵 below
Reposted by Austin Tripp
Valence Labs will be co-hosting a TechBio social with
@recursionpharma.bsky.social and NVIDIA at #NeurIPS in Vancouver.
Join us on Thurs, Dec 12th. RSVP here: lu.ma/biikt7ox
Our team will also be at NeurIPS throughout the week. See below for a summary of our papers👇
@recursionpharma.bsky.social and NVIDIA at #NeurIPS in Vancouver.
Join us on Thurs, Dec 12th. RSVP here: lu.ma/biikt7ox
Our team will also be at NeurIPS throughout the week. See below for a summary of our papers👇
A Night of Science with Recursion, Valence Labs, and NVIDIA @ NeurIPS 2024 · Luma
Recursion, Valence Labs, and NVIDIA is thrilled to extend an invitation to researchers, professors, investors, founders, students, and others interested in…
lu.ma
November 27, 2024 at 4:31 PM
Valence Labs will be co-hosting a TechBio social with
@recursionpharma.bsky.social and NVIDIA at #NeurIPS in Vancouver.
Join us on Thurs, Dec 12th. RSVP here: lu.ma/biikt7ox
Our team will also be at NeurIPS throughout the week. See below for a summary of our papers👇
@recursionpharma.bsky.social and NVIDIA at #NeurIPS in Vancouver.
Join us on Thurs, Dec 12th. RSVP here: lu.ma/biikt7ox
Our team will also be at NeurIPS throughout the week. See below for a summary of our papers👇
Reposted by Austin Tripp
The long and ugly story of Cassava Sciences’ supposed Alzheimer’s drug simufilam is finally over. It should have ended well before this.
The Cassava Saga Finally Ends
www.science.org
November 26, 2024 at 5:42 PM
The long and ugly story of Cassava Sciences’ supposed Alzheimer’s drug simufilam is finally over. It should have ended well before this.
Great quick blog post to understand benchmarks in drug discovery. My take: static datasets are probably not enough to prototype algorithms for discovery ‼️
From ImageNet sparking breakthroughs in computer vision, to CASP advancing protein structure prediction, competitions play a key role in driving innovation in ML. 🏆
🧵 We explore the current landscape of competitions in ML for drug discovery in our latest blog: polarishub.io/blog/driving...
🧵 We explore the current landscape of competitions in ML for drug discovery in our latest blog: polarishub.io/blog/driving...
November 22, 2024 at 6:23 PM
Great quick blog post to understand benchmarks in drug discovery. My take: static datasets are probably not enough to prototype algorithms for discovery ‼️
Reposted by Austin Tripp
Now I can share external links without the posts being down regulated - I thought it would share this again!:)
I have compiled a list of now 100+ companies in the 'TechBio' space into a fully open database for the community.
Find here and please share if you like
open.substack.com/pub/harrisbi...
I have compiled a list of now 100+ companies in the 'TechBio' space into a fully open database for the community.
Find here and please share if you like
open.substack.com/pub/harrisbi...
November 21, 2024 at 8:53 AM
Now I can share external links without the posts being down regulated - I thought it would share this again!:)
I have compiled a list of now 100+ companies in the 'TechBio' space into a fully open database for the community.
Find here and please share if you like
open.substack.com/pub/harrisbi...
I have compiled a list of now 100+ companies in the 'TechBio' space into a fully open database for the community.
Find here and please share if you like
open.substack.com/pub/harrisbi...