Joseph Viviano
@josephdviviano.bsky.social
humanistic technology bretheren @MILA_Quebec & @creativedlab Mentor ~ AI for Science ~ ex @deepgenomics & @CAMHResearch, intern @google & @imagia_ai ~ www.viviano.ca
Pinned
GitHub - GFNOrg/torchgfn: A modular, easy to extend GFlowNet library
A modular, easy to extend GFlowNet library. Contribute to GFNOrg/torchgfn development by creating an account on GitHub.
github.com
We’ve released torchgfn v2!
github.com/GFNOrg/torch...
We believe we’ve built the go-to library for fundamental GFlowNet methods development and prototyping, and we’re really excited to help you start using it.
github.com/GFNOrg/torch...
We believe we’ve built the go-to library for fundamental GFlowNet methods development and prototyping, and we’re really excited to help you start using it.
We’ve released torchgfn v2!
github.com/GFNOrg/torch...
We believe we’ve built the go-to library for fundamental GFlowNet methods development and prototyping, and we’re really excited to help you start using it.
github.com/GFNOrg/torch...
We believe we’ve built the go-to library for fundamental GFlowNet methods development and prototyping, and we’re really excited to help you start using it.
GitHub - GFNOrg/torchgfn: A modular, easy to extend GFlowNet library
A modular, easy to extend GFlowNet library. Contribute to GFNOrg/torchgfn development by creating an account on GitHub.
github.com
July 30, 2025 at 10:34 PM
We’ve released torchgfn v2!
github.com/GFNOrg/torch...
We believe we’ve built the go-to library for fundamental GFlowNet methods development and prototyping, and we’re really excited to help you start using it.
github.com/GFNOrg/torch...
We believe we’ve built the go-to library for fundamental GFlowNet methods development and prototyping, and we’re really excited to help you start using it.
Reposted by Joseph Viviano
Today marks a big milestone for me. I'm launching @law-zero.bsky.social, a nonprofit focusing on a new safe-by-design approach to AI that could both accelerate scientific discovery and provide a safeguard against the dangers of agentic AI.
Every frontier AI system should be grounded in a core commitment: to protect human joy and endeavour. Today, we launch LawZero, a nonprofit dedicated to advancing safe-by-design AI. lawzero.org
June 3, 2025 at 10:20 AM
Today marks a big milestone for me. I'm launching @law-zero.bsky.social, a nonprofit focusing on a new safe-by-design approach to AI that could both accelerate scientific discovery and provide a safeguard against the dangers of agentic AI.
Reposted by Joseph Viviano
America cannot long remain free, nor first among nations, if it becomes the kind of place where universities are dismantled because they don't align politically with the current head of the government.
May 23, 2025 at 4:00 PM
America cannot long remain free, nor first among nations, if it becomes the kind of place where universities are dismantled because they don't align politically with the current head of the government.
Reposted by Joseph Viviano
Preprint Alert 🚀
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
May 14, 2025 at 12:53 PM
Preprint Alert 🚀
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
Can we simultaneously learn transformation-invariant and transformation-equivariant representations with self-supervised learning?
TL;DR Yes! This is possible via simple predictive learning & architectural inductive biases – without extra loss terms and predictors!
🧵 (1/10)
Great job gang! And thanks to @boussifo.bsky.social for being such a stellar lead. (Also depicted: @jainmoksh.bsky.social)
April 25, 2025 at 12:51 AM
Great job gang! And thanks to @boussifo.bsky.social for being such a stellar lead. (Also depicted: @jainmoksh.bsky.social)
Ecstatic to show off some work my brilliant colleagues and I did at @iclr-conf.bsky.social this year! 🚀
We address the credit assignment challenge under long trajectories in RL or GFlowNets by constructing high order actions, or “chunks”, effectively compressing trajectory lengths!
We address the credit assignment challenge under long trajectories in RL or GFlowNets by constructing high order actions, or “chunks”, effectively compressing trajectory lengths!
April 4, 2025 at 4:45 PM
Ecstatic to show off some work my brilliant colleagues and I did at @iclr-conf.bsky.social this year! 🚀
We address the credit assignment challenge under long trajectories in RL or GFlowNets by constructing high order actions, or “chunks”, effectively compressing trajectory lengths!
We address the credit assignment challenge under long trajectories in RL or GFlowNets by constructing high order actions, or “chunks”, effectively compressing trajectory lengths!
Reposted by Joseph Viviano
From having to wrap a bunch of methods I can say I'm not a big fan of having configs in the form of argparsers.
March 5, 2025 at 4:42 AM
From having to wrap a bunch of methods I can say I'm not a big fan of having configs in the form of argparsers.
Reposted by Joseph Viviano
any economists here that can help me understand why the world's richest man might want to kill the consumer financial protection bureau
February 9, 2025 at 5:59 AM
any economists here that can help me understand why the world's richest man might want to kill the consumer financial protection bureau
Reposted by Joseph Viviano
Neural surrogates can accelerate PDE solving but need expensive ground-truth training data. Can we reduce the training data size with active learning (AL)? In our NeurIPS D3S3 poster, we introduce AL4PDE, an extensible AL benchmark for autoregressive neural PDE solvers. 🧵
December 11, 2024 at 6:22 PM
Neural surrogates can accelerate PDE solving but need expensive ground-truth training data. Can we reduce the training data size with active learning (AL)? In our NeurIPS D3S3 poster, we introduce AL4PDE, an extensible AL benchmark for autoregressive neural PDE solvers. 🧵
"The complaint alleges the algorithm, dubbed nH Predict, has a 90% error rate, basing that calculation on the percentage of payment denials reversed through internal appeals processes or administrative law judge rulings."
www.statnews.com/2023/11/14/u...
www.statnews.com/2023/11/14/u...
UnitedHealth faces class action lawsuit over algorithmic care denials in Medicare Advantage plans
A class action lawsuit was filed against UnitedHealth and a subsidiary alleging they use an algorithm to deny care to seriously ill patients
www.statnews.com
December 9, 2024 at 9:11 PM
"The complaint alleges the algorithm, dubbed nH Predict, has a 90% error rate, basing that calculation on the percentage of payment denials reversed through internal appeals processes or administrative law judge rulings."
www.statnews.com/2023/11/14/u...
www.statnews.com/2023/11/14/u...
Reposted by Joseph Viviano
Scalable emulation of protein equilibrium ensembles with
generative deep learning www.biorxiv.org/content/10.1...
No code is available yet, but sounds huge. Effectively does MD-sim, but fast!
generative deep learning www.biorxiv.org/content/10.1...
No code is available yet, but sounds huge. Effectively does MD-sim, but fast!
December 6, 2024 at 10:51 AM
Scalable emulation of protein equilibrium ensembles with
generative deep learning www.biorxiv.org/content/10.1...
No code is available yet, but sounds huge. Effectively does MD-sim, but fast!
generative deep learning www.biorxiv.org/content/10.1...
No code is available yet, but sounds huge. Effectively does MD-sim, but fast!
This book radically influenced my way of looking at human civilization and the kinds of tech that must be built to move us into a post sacristy, sustainable future. His story (overcoming failure/depression to produce major intellectual contributions outside the academic system was also formative.
December 5, 2024 at 4:45 AM
This book radically influenced my way of looking at human civilization and the kinds of tech that must be built to move us into a post sacristy, sustainable future. His story (overcoming failure/depression to produce major intellectual contributions outside the academic system was also formative.
Who are the top people working on computationally guided biosynthesis in the Boston / NY area?
December 4, 2024 at 11:21 PM
Who are the top people working on computationally guided biosynthesis in the Boston / NY area?
Reposted by Joseph Viviano
Mila is such a large community. One starter pack just isn’t enough! After @josephdviviano.bsky.social’s Mila list filled up, I decided to make another one. Will continue to add members until this one is full too.
go.bsky.app/9nXTDHo
go.bsky.app/9nXTDHo
November 27, 2024 at 1:49 PM
Mila is such a large community. One starter pack just isn’t enough! After @josephdviviano.bsky.social’s Mila list filled up, I decided to make another one. Will continue to add members until this one is full too.
go.bsky.app/9nXTDHo
go.bsky.app/9nXTDHo
Rupali is making the second Mila starter pack. Please reply to this if you're at Mila and she will add you.
I’m happy to make one. :)
November 27, 2024 at 7:17 AM
Rupali is making the second Mila starter pack. Please reply to this if you're at Mila and she will add you.
Reposted by Joseph Viviano
🚀 Did you know you can use the in-context learning abilities of an LLM to estimate the transition probabilities of a Markov chains?
The results are pretty exciting ! 😄
The results are pretty exciting ! 😄
November 26, 2024 at 2:52 PM
🚀 Did you know you can use the in-context learning abilities of an LLM to estimate the transition probabilities of a Markov chains?
The results are pretty exciting ! 😄
The results are pretty exciting ! 😄
Reposted by Joseph Viviano
BioM3: a model that generates proteins conditioned on text prompts, with wet-lab validation!
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
November 25, 2024 at 10:38 PM
BioM3: a model that generates proteins conditioned on text prompts, with wet-lab validation!
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
My suspicion is that we might be able to squeeze more juice out of the data with the correct training paradigm but what we're seeing in PLMs is similar to the saturation we're seeing in LLMs - every dataset/model pair will have a different S curve, with PLMs it is smaller.
Yet more evidence that transfer learning of sequence-only PLMs does not benefit from scale beyond 650M params 🧵
November 25, 2024 at 3:37 PM
My suspicion is that we might be able to squeeze more juice out of the data with the correct training paradigm but what we're seeing in PLMs is similar to the saturation we're seeing in LLMs - every dataset/model pair will have a different S curve, with PLMs it is smaller.
Reposted by Joseph Viviano
The complete guide for transfer learning with the protein language model ESM-2.
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
Scaling Down for Efficiency: Medium-Sized Transformer Models for Protein Sequence Transfer Learning
Protein language models such as the transformer-based Evolutionary Scale Modeling 2 (ESM2) can offer deep insights into evolutionary and structural properties of proteins. While larger models, such as...
www.biorxiv.org
November 25, 2024 at 2:50 AM
The complete guide for transfer learning with the protein language model ESM-2.
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
(In brief: Use ESM-2 650M and calculate mean embeddings across sites.)
www.biorxiv.org/content/10.1...
Reposted by Joseph Viviano
Kind of a broken record here but proceedings.neurips.cc/paper_files/...
is totally fascinating in that it postulates two underlying, measurable structures that you can use to assess if RL will be easy or hard in an environment
is totally fascinating in that it postulates two underlying, measurable structures that you can use to assess if RL will be easy or hard in an environment
November 23, 2024 at 6:18 PM
Kind of a broken record here but proceedings.neurips.cc/paper_files/...
is totally fascinating in that it postulates two underlying, measurable structures that you can use to assess if RL will be easy or hard in an environment
is totally fascinating in that it postulates two underlying, measurable structures that you can use to assess if RL will be easy or hard in an environment
Reposted by Joseph Viviano
I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!
go.bsky.app/AcP9Lix
go.bsky.app/AcP9Lix
November 10, 2024 at 12:11 AM
I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!
go.bsky.app/AcP9Lix
go.bsky.app/AcP9Lix
Hey @mubashariqbal.com please add: go.bsky.app/BHKxoss
November 22, 2024 at 1:02 PM
Hey @mubashariqbal.com please add: go.bsky.app/BHKxoss
Reposted by Joseph Viviano
And if you'd like to contribute or use these models, join our working group.
We're still starting up, so expect some rough edges but we've got a few really exciting projects lined up!
We're still starting up, so expect some rough edges but we've got a few really exciting projects lined up!
Materials and Chemistry | AI Alliance
We aim to curate datasets, tasks and benchmarks for materials science, build out foundation models in chemistry for prediction of properties, experimental outcomes or generation of new candidates and ...
thealliance.ai
November 7, 2024 at 5:15 PM
And if you'd like to contribute or use these models, join our working group.
We're still starting up, so expect some rough edges but we've got a few really exciting projects lined up!
We're still starting up, so expect some rough edges but we've got a few really exciting projects lined up!
I'm making an unofficial starter pack with some of my colleagues at Mila. WIP for now but here's the link!
go.bsky.app/BHKxoss
go.bsky.app/BHKxoss
November 20, 2024 at 3:19 PM
I'm making an unofficial starter pack with some of my colleagues at Mila. WIP for now but here's the link!
go.bsky.app/BHKxoss
go.bsky.app/BHKxoss