Jérémy Perez (@jeremy__perez) 's Twitter Profile
Jérémy Perez

@jeremy__perez

PhD Student in the @flowersinria team at @inria

ID: 1468563889310760961

calendar_today08-12-2021 12:52:01

56 Tweet

189 Followers

207 Following

Eleni Nisioti (@nisioti_eleni) 's Twitter Profile Photo

Almost time for ALIFE Conference 2025 where we will present our work "Collective Innovation in Groups of Large Language Models" We study how social structure affects how LLMs collectively play the game Little Alchemy 2 🔥+🌽=🍿 Work done with @Clement_MF_ Pierre-Yves Oudeyer Ida Momennejad Sebastian Risi

Iyad Rahwan | إياد رهوان (@iyadrahwan) 's Twitter Profile Photo

🚨 Paper Alert 🚨 AI learns everything from us human culture. But do we also learn from AI? Our paper *delves* into the question of whether humans have now started to speak like ChatGPT (not just write like it). Check out the video and thread below.

Stefano Palminteri (@stepalminteri.bsky.social) (@stepalminteri) 's Twitter Profile Photo

The conference will be basically opened by our own Maëva L'Hôtellier with a talk entitled "Achieving Scale-Independent Reinforcement Learning Performance With Reward Range Normalization" Friday October 11th (11:15 AM- 12:15 PM)

The conference will be basically opened by our own <a href="/MaevaLhotellier/">Maëva L'Hôtellier</a> with a talk entitled "Achieving Scale-Independent Reinforcement Learning Performance With Reward Range Normalization" 
Friday October 11th (11:15 AM- 12:15 PM)
Jérémy Perez (@jeremy__perez) 's Twitter Profile Photo

If you're interested in using LLMs to simulate artificial societies, or for human-AI collective intelligence, you might want to make sure that they can stick to the role/personality that you give them. This project led by Grgur Kovač introduces a leaderboard exactly for that!

Inria Flowers team (@flowersinria) 's Twitter Profile Photo

Excited to share with @flowersINRIA ADTool, an open-source Python toolkit using curiosity-driven AI to explore behavior diversity of complex systems (cellular automata, physics models, ...)!🐍 Serving off-the-shelf strategies like IMGEP github.com/flowersteam/ad… You said IMGEP? 👇

Xavier Hinaut (@neuronalx) 's Twitter Profile Photo

J-6 pour s'inscrire au #hackathon Hack1robo ! 🚀 Choisi ton challenge parmi 8 projets sur les thèmes #IA #robot #sciencescognitives sites.google.com/view/hack1robo… Encore 25 places ! Inscriptions ➡️ helloasso.com/associations/a… Inria Bordeaux Neurocampus Bordeaux Tien Vu Université de Bordeaux

J-6 pour s'inscrire au #hackathon Hack1robo ! 🚀

Choisi ton challenge parmi 8 projets sur les thèmes #IA #robot #sciencescognitives
sites.google.com/view/hack1robo…

Encore 25 places !
Inscriptions ➡️ helloasso.com/associations/a…

<a href="/Inria/">Inria</a> <a href="/Neuro_Bordeaux/">Bordeaux Neurocampus</a> <a href="/Bordeaux/">Bordeaux</a> <a href="/aquinum/">Tien Vu</a>  <a href="/univbordeaux/">Université de Bordeaux</a>
Jérémy Perez (@jeremy__perez) 's Twitter Profile Photo

🚀 #Hack1robo is approaching!! 🚀 Together with Sina K. and Marko Cvjetko, we propose to explore what happens when you plug music into continuous cellular automata: 🎶+ 🦠 = ? If you're in Bordeaux 15th to 17th November, come explore this topic with us! -6 days to register

Nicolas Yax (@nicolas__yax) 's Twitter Profile Photo

🚨New preprint🚨 When testing LLMs with questions, how can we know they did not see the answer in their training? In this new paper we propose a simple out of the box and fast method to spot contamination on short texts with Stefano Palminteri (@stepalminteri.bsky.social) and Pierre-Yves Oudeyer ! 1/16

🚨New preprint🚨
When testing LLMs with questions, how can we know they did not see the answer in their training? In this new paper we propose a simple out of the box and fast method to spot contamination on short texts with <a href="/StePalminteri/">Stefano Palminteri (@stepalminteri.bsky.social)</a> and <a href="/pyoudeyer/">Pierre-Yves Oudeyer</a> ! 1/16
Jérémy Perez (@jeremy__perez) 's Twitter Profile Photo

📢Open position: Master internship on hybrid human-LLM cultural evolution We're looking for an intern to explore how LLMs can help human groups discover, select and transmit solutions to problems More info and other positions here: flowers.inria.fr/jobs/ and in thread below

Nicolas Yax (@nicolas__yax) 's Twitter Profile Photo

🔥Our paper PhyloLM got accepted at ICLR 2025 !🔥 In this work we show how easy it can be to infer relationship between LLMs by constructing trees and to predict their performances and behavior at a very low cost with Stefano Palminteri (@stepalminteri.bsky.social) and Pierre-Yves Oudeyer ! Here is a brief recap ⬇️