@silver-soliloquy.bsky.social
Engineer, Doctoral Student, Data Wizard (Rogers 2020).
Reposted
Knowledge Graph Foundation Models (KGFMs) are at the frontier of graph learning - but we didn’t have a principled understanding of what we can (or can’t) do with them. Now we do! 💡🚀🧵
With Pablo Barcelo, Ismail Ceylan, @mmbronstein.bsky.social , @mgalkin.bsky.social, Juan Reutter, Miguel Romero!
With Pablo Barcelo, Ismail Ceylan, @mmbronstein.bsky.social , @mgalkin.bsky.social, Juan Reutter, Miguel Romero!
February 24, 2025 at 7:32 PM
Knowledge Graph Foundation Models (KGFMs) are at the frontier of graph learning - but we didn’t have a principled understanding of what we can (or can’t) do with them. Now we do! 💡🚀🧵
With Pablo Barcelo, Ismail Ceylan, @mmbronstein.bsky.social , @mgalkin.bsky.social, Juan Reutter, Miguel Romero!
With Pablo Barcelo, Ismail Ceylan, @mmbronstein.bsky.social , @mgalkin.bsky.social, Juan Reutter, Miguel Romero!
The huggingface agents course starts on Feb 10th. Looks promising: huggingface.co/agents-course
agents-course (Hugging Face Agents Course)
Org profile for Hugging Face Agents Course on Hugging Face, the AI community building the future.
huggingface.co
February 8, 2025 at 2:42 PM
The huggingface agents course starts on Feb 10th. Looks promising: huggingface.co/agents-course
Reposted
🚨Our paper on how the cerebellum learns to drive cortical dynamics for rapid task learning and switching, which we propose can then be consolidated in the cortex @naturecomms.bsky.social
nature.com/articles/s41...
🧠 #compneuro
nature.com/articles/s41...
🧠 #compneuro
January 2, 2025 at 12:07 PM
🚨Our paper on how the cerebellum learns to drive cortical dynamics for rapid task learning and switching, which we propose can then be consolidated in the cortex @naturecomms.bsky.social
nature.com/articles/s41...
🧠 #compneuro
nature.com/articles/s41...
🧠 #compneuro
Reposted
An excellent overview of mechanistic interpretability.
youtu.be/UGO_Ehywuxc
youtu.be/UGO_Ehywuxc
The Dark Matter of AI [Mechanistic Interpretability]
YouTube video by Welch Labs
youtu.be
December 26, 2024 at 1:34 AM
An excellent overview of mechanistic interpretability.
youtu.be/UGO_Ehywuxc
youtu.be/UGO_Ehywuxc
Reposted
HBO has declined to renew “Sesame Street” for new episodes. The series that’s been teaching generations of little kids since 1969 now has no studio.
Please consider donating to Sesame Workshop to ensure the residents of 123 Sesame Street are still around to teach kids of all needs and backgrounds.
Please consider donating to Sesame Workshop to ensure the residents of 123 Sesame Street are still around to teach kids of all needs and backgrounds.
Support Us - Sesame Workshop
Individual donors and partners can have a major impact. Join Sesame Workshop’s Mission to Help Kids Everywhere Grow Smarter, Stronger, and Kinder.
sesameworkshop.org
December 15, 2024 at 2:12 PM
HBO has declined to renew “Sesame Street” for new episodes. The series that’s been teaching generations of little kids since 1969 now has no studio.
Please consider donating to Sesame Workshop to ensure the residents of 123 Sesame Street are still around to teach kids of all needs and backgrounds.
Please consider donating to Sesame Workshop to ensure the residents of 123 Sesame Street are still around to teach kids of all needs and backgrounds.
Reposted
Interested in AI for scientific discovery? Our research team has four workshop presentations at NeurIPS that span LLM mechanistic interpretability, graph neural networks, and diffusion models -- all presented today!
A 🧵 of our results below (each paper is linked):
A 🧵 of our results below (each paper is linked):
December 15, 2024 at 3:56 PM
Interested in AI for scientific discovery? Our research team has four workshop presentations at NeurIPS that span LLM mechanistic interpretability, graph neural networks, and diffusion models -- all presented today!
A 🧵 of our results below (each paper is linked):
A 🧵 of our results below (each paper is linked):
Reposted
Normalizing Flows are Capable Generative Models
Apple introduces TarFlow, a new Transformer-based variant of Masked Autoregressive Flows.
SOTA on likelihood estimation for images, quality and diversity comparable to diffusion models.
arxiv.org/abs/2412.06329
Apple introduces TarFlow, a new Transformer-based variant of Masked Autoregressive Flows.
SOTA on likelihood estimation for images, quality and diversity comparable to diffusion models.
arxiv.org/abs/2412.06329
Normalizing Flows are Capable Generative Models
Normalizing Flows (NFs) are likelihood-based models for continuous inputs.
They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relati...
arxiv.org
December 10, 2024 at 8:06 AM
Normalizing Flows are Capable Generative Models
Apple introduces TarFlow, a new Transformer-based variant of Masked Autoregressive Flows.
SOTA on likelihood estimation for images, quality and diversity comparable to diffusion models.
arxiv.org/abs/2412.06329
Apple introduces TarFlow, a new Transformer-based variant of Masked Autoregressive Flows.
SOTA on likelihood estimation for images, quality and diversity comparable to diffusion models.
arxiv.org/abs/2412.06329
Reposted
Entropy is one of those formulas that many of us learn, swallow whole, and even use regularly without really understanding.
(E.g., where does that “log” come from? Are there other possible formulas?)
Yet there's an intuitive & almost inevitable way to arrive at this expression.
(E.g., where does that “log” come from? Are there other possible formulas?)
Yet there's an intuitive & almost inevitable way to arrive at this expression.
December 9, 2024 at 10:44 PM
Entropy is one of those formulas that many of us learn, swallow whole, and even use regularly without really understanding.
(E.g., where does that “log” come from? Are there other possible formulas?)
Yet there's an intuitive & almost inevitable way to arrive at this expression.
(E.g., where does that “log” come from? Are there other possible formulas?)
Yet there's an intuitive & almost inevitable way to arrive at this expression.
Reposted
Multiplicative noise is good! 🎲
Just make your neural network weights noisy (like 🧠?) and reap the benefits of robustness to corruptions with no loss on clean data.
🌟Spotlight paper at #NeurIPS2024 led by Trung Trinh & w/ Markus Heinonen and @samikaski.bsky.social
trungtrinh44.github.io/DAMP/
Just make your neural network weights noisy (like 🧠?) and reap the benefits of robustness to corruptions with no loss on clean data.
🌟Spotlight paper at #NeurIPS2024 led by Trung Trinh & w/ Markus Heinonen and @samikaski.bsky.social
trungtrinh44.github.io/DAMP/
Improving robustness to corruptions with multiplicative weight perturbations
Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski
trungtrinh44.github.io
December 9, 2024 at 8:49 AM
Multiplicative noise is good! 🎲
Just make your neural network weights noisy (like 🧠?) and reap the benefits of robustness to corruptions with no loss on clean data.
🌟Spotlight paper at #NeurIPS2024 led by Trung Trinh & w/ Markus Heinonen and @samikaski.bsky.social
trungtrinh44.github.io/DAMP/
Just make your neural network weights noisy (like 🧠?) and reap the benefits of robustness to corruptions with no loss on clean data.
🌟Spotlight paper at #NeurIPS2024 led by Trung Trinh & w/ Markus Heinonen and @samikaski.bsky.social
trungtrinh44.github.io/DAMP/
Reposted
One of the best tutorials for understanding Transformers!
📽️ Watch here: www.youtube.com/watch?v=bMXq...
Big thanks to @giffmana.ai for this excellent content! 🙌
📽️ Watch here: www.youtube.com/watch?v=bMXq...
Big thanks to @giffmana.ai for this excellent content! 🙌
[M2L 2024] Transformers - Lucas Beyer
YouTube video by Mediterranean Machine Learning (M2L) summer school
www.youtube.com
December 8, 2024 at 9:58 AM
One of the best tutorials for understanding Transformers!
📽️ Watch here: www.youtube.com/watch?v=bMXq...
Big thanks to @giffmana.ai for this excellent content! 🙌
📽️ Watch here: www.youtube.com/watch?v=bMXq...
Big thanks to @giffmana.ai for this excellent content! 🙌
Reposted
Super happy to reveal our new paper! 🎉🙌♟️
We trained a model to play four games, and the performance in each increases by "external search" (MCTS using a learned world model) and "internal search" where the model outputs the whole plan on its own!
We trained a model to play four games, and the performance in each increases by "external search" (MCTS using a learned world model) and "internal search" where the model outputs the whole plan on its own!
December 5, 2024 at 9:09 AM
Super happy to reveal our new paper! 🎉🙌♟️
We trained a model to play four games, and the performance in each increases by "external search" (MCTS using a learned world model) and "internal search" where the model outputs the whole plan on its own!
We trained a model to play four games, and the performance in each increases by "external search" (MCTS using a learned world model) and "internal search" where the model outputs the whole plan on its own!
Reposted
We are organising the First International Conference on Probabilistic Numerics (ProbNum 2025) at EURECOM in southern France in Sep 2025. Topics: AI, ML, Stat, Sim, and Numerics. Reposts very much appreciated!
probnum25.github.io
probnum25.github.io
November 17, 2024 at 7:06 AM
We are organising the First International Conference on Probabilistic Numerics (ProbNum 2025) at EURECOM in southern France in Sep 2025. Topics: AI, ML, Stat, Sim, and Numerics. Reposts very much appreciated!
probnum25.github.io
probnum25.github.io
Reposted
I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty.
paper: arxiv.org/abs/2406.07658
repo: github.com/blei-lab/tre...
🧵(1/8)
paper: arxiv.org/abs/2406.07658
repo: github.com/blei-lab/tre...
🧵(1/8)
December 2, 2024 at 9:48 PM
I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty.
paper: arxiv.org/abs/2406.07658
repo: github.com/blei-lab/tre...
🧵(1/8)
paper: arxiv.org/abs/2406.07658
repo: github.com/blei-lab/tre...
🧵(1/8)
Reposted
I was deeply disappointed by the lack of nature/science/climate/enviro on many major end-of-year book lists—so I decided to make my own!
Introducing: ✨🎁📚 The 2024 Holiday Gift Guide to Nature & Science Books ✨🎁📚
Please share: Let's make this go viral in time for Black Friday / holiday shopping!
Introducing: ✨🎁📚 The 2024 Holiday Gift Guide to Nature & Science Books ✨🎁📚
Please share: Let's make this go viral in time for Black Friday / holiday shopping!
November 27, 2024 at 7:08 PM
I was deeply disappointed by the lack of nature/science/climate/enviro on many major end-of-year book lists—so I decided to make my own!
Introducing: ✨🎁📚 The 2024 Holiday Gift Guide to Nature & Science Books ✨🎁📚
Please share: Let's make this go viral in time for Black Friday / holiday shopping!
Introducing: ✨🎁📚 The 2024 Holiday Gift Guide to Nature & Science Books ✨🎁📚
Please share: Let's make this go viral in time for Black Friday / holiday shopping!
Reposted
Bayesball! www.biorxiv.org/content/10.1... The Bayesian nature of baseball. From Brantley & @kordinglab.bsky.social
November 21, 2024 at 8:45 PM
Bayesball! www.biorxiv.org/content/10.1... The Bayesian nature of baseball. From Brantley & @kordinglab.bsky.social
Reposted
An employee of Huggingface, a site of AI training datasets, made a dataset of a million Bluesky posts scraped simply because they could. It’s currently trending: www.404media.co/someone-made...
Someone Made a Dataset of One Million Bluesky Posts for 'Machine Learning Research'
A Hugging Face employee made a huge dataset of Bluesky posts, and it’s already very popular.
www.404media.co
November 27, 2024 at 12:09 AM
An employee of Huggingface, a site of AI training datasets, made a dataset of a million Bluesky posts scraped simply because they could. It’s currently trending: www.404media.co/someone-made...
Reposted
There’s a single formula that makes all of your diffusion models possible: Tweedie's
Say 𝐱 is a noisy version of 𝐮 with 𝐞 ∼ 𝒩(𝟎, σ² 𝐈)
𝐱 = 𝐮 + 𝐞
MMSE estimate of 𝐮 is 𝔼[𝐮|𝐱] & would seem to require P(𝐮|𝐱). Yet Tweedie says P(𝐱) is all you need
1/3
Say 𝐱 is a noisy version of 𝐮 with 𝐞 ∼ 𝒩(𝟎, σ² 𝐈)
𝐱 = 𝐮 + 𝐞
MMSE estimate of 𝐮 is 𝔼[𝐮|𝐱] & would seem to require P(𝐮|𝐱). Yet Tweedie says P(𝐱) is all you need
1/3
November 22, 2024 at 9:45 PM
There’s a single formula that makes all of your diffusion models possible: Tweedie's
Say 𝐱 is a noisy version of 𝐮 with 𝐞 ∼ 𝒩(𝟎, σ² 𝐈)
𝐱 = 𝐮 + 𝐞
MMSE estimate of 𝐮 is 𝔼[𝐮|𝐱] & would seem to require P(𝐮|𝐱). Yet Tweedie says P(𝐱) is all you need
1/3
Say 𝐱 is a noisy version of 𝐮 with 𝐞 ∼ 𝒩(𝟎, σ² 𝐈)
𝐱 = 𝐮 + 𝐞
MMSE estimate of 𝐮 is 𝔼[𝐮|𝐱] & would seem to require P(𝐮|𝐱). Yet Tweedie says P(𝐱) is all you need
1/3
Reposted
For those who missed this post on the-network-that-is-not-to-be-named, I made public my "secrets" for writing a good CVPR paper (or any scientific paper). I've compiled these tips of many years. It's long but hopefully it helps people write better papers. perceiving-systems.blog/en/post/writ...
Writing a good scientific paper
perceiving-systems.blog
November 20, 2024 at 10:18 AM
For those who missed this post on the-network-that-is-not-to-be-named, I made public my "secrets" for writing a good CVPR paper (or any scientific paper). I've compiled these tips of many years. It's long but hopefully it helps people write better papers. perceiving-systems.blog/en/post/writ...
Reposted
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
November 22, 2024 at 1:33 AM
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
Reposted
Postdoc opportunities! The Johns Hopkins Data Science and AI Institute has a new postdoc program!
We’re looking for candidates across data science and AI, including science, health, medicine, the humanities, engineering, policy, and ethics.
Spread the word and apply!
ai.jhu.edu/postdoctoral...
We’re looking for candidates across data science and AI, including science, health, medicine, the humanities, engineering, policy, and ethics.
Spread the word and apply!
ai.jhu.edu/postdoctoral...
Postdoctoral Fellowship Program - Johns Hopkins Data Science and AI Institute
Data Science and AI Institute Postdoctoral Fellowship Program The Johns Hopkins Data Science and AI Institute welcomes applications for its postdoctoral fellowship program, seeking scholars to advance...
ai.jhu.edu
November 17, 2024 at 1:01 AM
Postdoc opportunities! The Johns Hopkins Data Science and AI Institute has a new postdoc program!
We’re looking for candidates across data science and AI, including science, health, medicine, the humanities, engineering, policy, and ethics.
Spread the word and apply!
ai.jhu.edu/postdoctoral...
We’re looking for candidates across data science and AI, including science, health, medicine, the humanities, engineering, policy, and ethics.
Spread the word and apply!
ai.jhu.edu/postdoctoral...
Reposted
I'm slowly putting my intro to ML course material on github, starting with the lab sessions: github.com/davidpicard/...
These are self-contained notebooks in which you have to implement famous algorithms from the literature (k-NN, SVM, DT, etc), with a custom dataset that I (painstakingly) made!
These are self-contained notebooks in which you have to implement famous algorithms from the literature (k-NN, SVM, DT, etc), with a custom dataset that I (painstakingly) made!
November 19, 2024 at 2:30 PM
I'm slowly putting my intro to ML course material on github, starting with the lab sessions: github.com/davidpicard/...
These are self-contained notebooks in which you have to implement famous algorithms from the literature (k-NN, SVM, DT, etc), with a custom dataset that I (painstakingly) made!
These are self-contained notebooks in which you have to implement famous algorithms from the literature (k-NN, SVM, DT, etc), with a custom dataset that I (painstakingly) made!
Reposted
Even as an interpretable ML researcher, I wasn't sure what to make of Mechanistic Interpretability, which seemed to come out of nowhere not too long ago.
But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.
But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.
November 20, 2024 at 8:00 AM
Even as an interpretable ML researcher, I wasn't sure what to make of Mechanistic Interpretability, which seemed to come out of nowhere not too long ago.
But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.
But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.
Reposted
Since this platform is finally attracting a critical mass of ML researchers, here's our recent work on prompt-based vulnerabilities of coding assistants:
arxiv.org/abs/2407.11072
TL;DR — An attacker can convince your favorite LLM to suggest vulnerable code with just a minor change to the prompt!
arxiv.org/abs/2407.11072
TL;DR — An attacker can convince your favorite LLM to suggest vulnerable code with just a minor change to the prompt!
MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants
LLM-based programming assistants offer the promise of programming faster but with the risk of introducing more security vulnerabilities. Prior work has studied how LLMs could be maliciously fine-tuned...
arxiv.org
November 17, 2024 at 11:41 PM
Since this platform is finally attracting a critical mass of ML researchers, here's our recent work on prompt-based vulnerabilities of coding assistants:
arxiv.org/abs/2407.11072
TL;DR — An attacker can convince your favorite LLM to suggest vulnerable code with just a minor change to the prompt!
arxiv.org/abs/2407.11072
TL;DR — An attacker can convince your favorite LLM to suggest vulnerable code with just a minor change to the prompt!
Reposted
I still have to finish reading this post but it’s the first time even since the transformer paper I feel like grok what “positional encoding” really is.
fleetwood.dev/posts/you-co...
fleetwood.dev/posts/you-co...
November 18, 2024 at 10:50 PM
I still have to finish reading this post but it’s the first time even since the transformer paper I feel like grok what “positional encoding” really is.
fleetwood.dev/posts/you-co...
fleetwood.dev/posts/you-co...