Justin Deschenaux
@jdeschena.bsky.social
PhD student @EPFL, supervised by Caglar Gulcehre. Casting the forces of gradient descent 🧙♂️
Website: https://jdeschena.github.io
Website: https://jdeschena.github.io
Reposted by Justin Deschenaux
Excited to share our latest work on EvoTune, a novel method integrating LLM-guided evolutionary search and reinforcement learning to accelerate the discovery of algorithms! 1/12🧵
April 26, 2025 at 4:56 PM
Excited to share our latest work on EvoTune, a novel method integrating LLM-guided evolutionary search and reinforcement learning to accelerate the discovery of algorithms! 1/12🧵
Reposted by Justin Deschenaux
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 Justin Deschenaux
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)
Reposted by Justin Deschenaux
A paper a day keeps the FOMO away, episode 7.
Among "oldies but goldies", this tutorial by Rabiner on Hidden Markov Models (HMMs) is dear to my heart. HMMs are one of the simplest statistical models where some variables are not observed, and we love them for it. 🧵
www.cs.ubc.ca/~murphyk/Bay...
Among "oldies but goldies", this tutorial by Rabiner on Hidden Markov Models (HMMs) is dear to my heart. HMMs are one of the simplest statistical models where some variables are not observed, and we love them for it. 🧵
www.cs.ubc.ca/~murphyk/Bay...
www.cs.ubc.ca
November 19, 2024 at 10:40 AM
A paper a day keeps the FOMO away, episode 7.
Among "oldies but goldies", this tutorial by Rabiner on Hidden Markov Models (HMMs) is dear to my heart. HMMs are one of the simplest statistical models where some variables are not observed, and we love them for it. 🧵
www.cs.ubc.ca/~murphyk/Bay...
Among "oldies but goldies", this tutorial by Rabiner on Hidden Markov Models (HMMs) is dear to my heart. HMMs are one of the simplest statistical models where some variables are not observed, and we love them for it. 🧵
www.cs.ubc.ca/~murphyk/Bay...
Reposted by Justin Deschenaux
In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome!
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
November 15, 2024 at 8:04 PM
In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome!
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔