Loris Gaven (@lorisgaven) 's Twitter Profile
Loris Gaven

@lorisgaven

Striving to make computers smarter.
PhD student @FlowersINRIA

ID: 1650224511290056706

linkhttps://lgaven.me calendar_today23-04-2023 19:46:13

20 Tweet

44 Followers

364 Following

Joel Lehman (@joelbot3000) 's Twitter Profile Photo

new paper: "Evolution and the Knightian Blindspot of Machine Learning" Our ever-changing world bubbles with surprise and complexity. General AI must include handling unforeseen situations with grace. Yet this issue largely lies outside AI's formalisms: a blind spot. (1/n)

Corentin LEGER (@corentinlger) 's Twitter Profile Photo

🚀 Want to simulate #AI/#ALife agents in a physics-driven world? Meet Vivarium🌱– a new multi-agent simulator from Inria Flowers team , designed for research & education! ✅ Large-scale simulations with #JAX ✅ User-friendly web interface ✅ Real-time control with jupyter notebooks

Carta Thomas (@cartathomas2) 's Twitter Profile Photo

🚀 Introducing 🧭MAGELLAN—our new metacognitive framework for LLM agents! It predicts its own learning progress (LP) in vast natural language goal spaces, enabling efficient exploration of complex domains.🌍✨Learn more: 🔗 arxiv.org/abs/2502.07709 #OpenEndedLearning #LLM #RL

Pierre-Yves Oudeyer (@pyoudeyer) 's Twitter Profile Photo

🧠 One of the key limitation of LLMs today is their lack of metacognition: they were (mostly) not trained to know what they know or don't know, what they can or can't do. 🚀At Inria Flowers team, we're proposing an approach to build metacognition into LLMs: MAGELLAN !

🧠 One of the key limitation of LLMs today is their lack of metacognition:  they were (mostly) not trained to know what they know or don't know, what they can or can't do.

🚀At <a href="/FlowersINRIA/">Inria Flowers team</a>, we're proposing an approach to build metacognition into LLMs: MAGELLAN !
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 ⬇️

Cédric (@cedcolas) 's Twitter Profile Photo

i just got an art grant from the council for the arts at MIT! *Tangible Dreams* will let visitors experiment and play with a physical neural network generating images real-time—by twisting knobs and switches, by reconnecting nodes together Arts at MIT

i just got an art grant from the council for the arts at MIT!

*Tangible Dreams* will let visitors experiment and play with a physical neural network generating images real-time—by twisting knobs and switches, by reconnecting  nodes together <a href="/ArtsatMIT/">Arts at MIT</a>
Minqi Jiang (@minqijiang) 's Twitter Profile Photo

It's so fun to see RL finally work on complex real-world tasks with LLM policies, but it's increasingly clear that we lack an understanding of how RL fine-tuning leads to generalization. In the same week, we got two (awesome) papers: Absolute Zero Reasoner: Improvements on code

It's so fun to see RL finally work on complex real-world tasks with LLM policies, but it's increasingly clear that we lack an understanding of how RL fine-tuning leads to generalization.

In the same week, we got two (awesome) papers:

Absolute Zero Reasoner: Improvements on code
Jenny Zhang (@jennyzhangzt) 's Twitter Profile Photo

**When AIs Start Rewriting Themselves** Darwin G​​ödel Machine: Open-Ended Evolution of Self-Improving Agents The Darwin G​​ödel Machine can: 1. Read and modify its own code 2. Evaluate if the change improves performance 3. Open-endedly explore the solution space 🧵👇

Pierre-Yves Oudeyer (@pyoudeyer) 's Twitter Profile Photo

New blog post ! What if LLM agents could learn by doing, not just by reading? 🤔 2024 was the year of "agentic AI"—systems that plan, act, and execute complex workflows autonomously. But current agents face critical limitations... 🧵

Clément ROMAC (@clementromac) 's Twitter Profile Photo

I'll be at RLDM this week to present our new paper: WorldLLM 😃 In the same spirit as our previous works — e.g. GLAM, MAGELLAN... — which investigate how to ground LLMs through interactions with external environments, WorldLLM takes a deep dive into the world modeling aspect.

Cédric (@cedcolas) 's Twitter Profile Photo

IMOL conference happening in the UK, sept 8-10 registration is free! send an extended abstract by july 13 pls retweet if you have IMOL-adjacent followers!

Pourcel Julien (@pourceljulien) 's Twitter Profile Photo

Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #ICML!) It brings LLMs from just a few percent on ARC-AGI-1 up to 52% We’re releasing the finetuned LLMs, a dataset of 5M generated programs and the code. 🧵

Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #ICML!)

It brings LLMs from just a few percent on ARC-AGI-1 up to 52%

We’re releasing the finetuned LLMs, a dataset of 5M generated programs and the code.

🧵
Cansu Sancaktar (@ccansusancaktar) 's Twitter Profile Photo

✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs. With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk. Accepted at ICML 2025🎉 Joint work with Christian Gumbsch 🧵

Clément ROMAC (@clementromac) 's Twitter Profile Photo

I'm attending ICML 2025 this week in Vancouver where we're presenting our MAGELLAN paper along with Loris Gaven and Carta Thomas! 📅 Come discuss at our poster session on July 17 at 11 am East Exhibition Hall A-B E-2803 Or reach out for a chat! x.com/CartaThomas2/s…