Tim Davidson
@imtd.bsky.social
🌐 https://www.trdavidson.com
🔬research: deep generative learning; agentic systems; synthetic data
PhD @EPFL on reliable magic
Spent time @MSR, @Google
machine learning & company building
🎓@NYU @UvA alumn
🔬research: deep generative learning; agentic systems; synthetic data
PhD @EPFL on reliable magic
Spent time @MSR, @Google
machine learning & company building
🎓@NYU @UvA alumn
Reposted by Tim Davidson
A dream come true! I presented "No Representation, No Trust" on my favorite RL podcast, TalkRL!
Make sure to check it out to learn why training with PPO for too long makes your agent collapse!
Make sure to check it out to learn why training with PPO for too long makes your agent collapse!
E63: NeurIPS 2024 - Posters and Hallways 1
Jiaheng Hu of UTexas on Unsupervised Skill Discovery for HRL
@skandermoalla.bsky.social of EPFL: Representation and Trust in PPO
Adil Zouitine of IRT Saint Exupery/Hugging Face : Time-Constrained Robust MDPs
Jiaheng Hu of UTexas on Unsupervised Skill Discovery for HRL
@skandermoalla.bsky.social of EPFL: Representation and Trust in PPO
Adil Zouitine of IRT Saint Exupery/Hugging Face : Time-Constrained Robust MDPs
March 3, 2025 at 9:36 PM
A dream come true! I presented "No Representation, No Trust" on my favorite RL podcast, TalkRL!
Make sure to check it out to learn why training with PPO for too long makes your agent collapse!
Make sure to check it out to learn why training with PPO for too long makes your agent collapse!
Reposted by Tim Davidson
🔥 Want to train large neural networks WITHOUT Adam while using less memory and getting better results? ⚡
Check out SCION: a new optimizer that adapts to the geometry of your problem using norm-constrained linear minimization oracles (LMOs): 🧵👇
Check out SCION: a new optimizer that adapts to the geometry of your problem using norm-constrained linear minimization oracles (LMOs): 🧵👇
February 13, 2025 at 4:51 PM
🔥 Want to train large neural networks WITHOUT Adam while using less memory and getting better results? ⚡
Check out SCION: a new optimizer that adapts to the geometry of your problem using norm-constrained linear minimization oracles (LMOs): 🧵👇
Check out SCION: a new optimizer that adapts to the geometry of your problem using norm-constrained linear minimization oracles (LMOs): 🧵👇
Reposted by Tim Davidson
Here's Veo 2, the latest version of our video generation model, as well as a substantial upgrade for Imagen 3 🧑🍳🚢
(Did I mention we are hiring on the Generative Media team, btw 👀)
blog.google/technology/g...
(Did I mention we are hiring on the Generative Media team, btw 👀)
blog.google/technology/g...
State-of-the-art video and image generation with Veo 2 and Imagen 3
We’re rolling out a new, state-of-the-art video model, Veo 2, and updates to Imagen 3. Plus, check out our new experiment, Whisk.
blog.google
December 16, 2024 at 5:35 PM
Here's Veo 2, the latest version of our video generation model, as well as a substantial upgrade for Imagen 3 🧑🍳🚢
(Did I mention we are hiring on the Generative Media team, btw 👀)
blog.google/technology/g...
(Did I mention we are hiring on the Generative Media team, btw 👀)
blog.google/technology/g...
lol. yes, very true and important
the crucial first step in fighting anthropomorphization of DL systems is to find an easier to write and pronounce word than anthropomorphizing.
December 15, 2024 at 4:32 PM
lol. yes, very true and important
Reposted by Tim Davidson
Also, check out our ML project template—it’s a game-changer!🚀🚀
@caglarai.bsky.social
🧑💻 github.com/CLAIRE-Labo/...
@caglarai.bsky.social
🧑💻 github.com/CLAIRE-Labo/...
December 10, 2024 at 7:39 PM
Also, check out our ML project template—it’s a game-changer!🚀🚀
@caglarai.bsky.social
🧑💻 github.com/CLAIRE-Labo/...
@caglarai.bsky.social
🧑💻 github.com/CLAIRE-Labo/...
Reposted by Tim Davidson
I am in Vancouver for NeurIPS 2024 until December 16th if you want to meet, DM or email me.
We have two accepted papers from my lab:
1. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers, on Wednesday, East Exhibit Hall A-C #2010 (1/3)
We have two accepted papers from my lab:
1. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers, on Wednesday, East Exhibit Hall A-C #2010 (1/3)
December 9, 2024 at 11:04 PM
I am in Vancouver for NeurIPS 2024 until December 16th if you want to meet, DM or email me.
We have two accepted papers from my lab:
1. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers, on Wednesday, East Exhibit Hall A-C #2010 (1/3)
We have two accepted papers from my lab:
1. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers, on Wednesday, East Exhibit Hall A-C #2010 (1/3)
favorite conference experience for me :)
The Uncertainty in Artificial Intelligence conference (UAI) is on 🦋!
I'm a bit biased, but this is a fantastic conference for #probabilisticML, #causality, #causalML, #tractable #probabilistic #models, #imprecise probabilities,
#reasoning, #neurosymbolic approaches and more.
#causalSky #statSky
I'm a bit biased, but this is a fantastic conference for #probabilisticML, #causality, #causalML, #tractable #probabilistic #models, #imprecise probabilities,
#reasoning, #neurosymbolic approaches and more.
#causalSky #statSky
We are the premier conference on #uncertainty in #AI and #ML since 1985 🧓
Hello, 🦋!
Follow us to reduce uncertainty!
Hello, 🦋!
Follow us to reduce uncertainty!
December 3, 2024 at 4:59 PM
favorite conference experience for me :)
Reposted by Tim Davidson
Better VQ-VAEs with this one weird rotation trick!
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
December 2, 2024 at 7:52 PM
Better VQ-VAEs with this one weird rotation trick!
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
Reposted by Tim Davidson
I've put together a starter pack of EPFL researchers across all labs and domains! 🇨🇭 Would love to expand this list and showcase more amazing work happening at EPFL. Drop a reply to be added!
#EPFL #academicsky
go.bsky.app/73zdbtp
#EPFL #academicsky
go.bsky.app/73zdbtp
November 22, 2024 at 2:41 PM
I've put together a starter pack of EPFL researchers across all labs and domains! 🇨🇭 Would love to expand this list and showcase more amazing work happening at EPFL. Drop a reply to be added!
#EPFL #academicsky
go.bsky.app/73zdbtp
#EPFL #academicsky
go.bsky.app/73zdbtp