Arthur

🤖 PhD student at @ULiege 🎓 | Co-Founder of Belerion

[Damien ERNST @DamienERNST1]

Great meeting today with the people of the NSPA, the procurement agency of NATO, for discussing about our work around AI for Defense.

I am very proud of the extraordinary work carried out by all those bright young researchers of the group. We are moving forward very rapidly.
Here is a link to a paper that describes our technological roadmap:
https://t.co/L28QUUNJyG

[Pascal Leroy @PaLeroy]

Interesting to link asymmetric learning and CTDE in MARL!

[Arthur @arthurlouette]

Paper published: “Existing Gaps in Reinforcement Learning for Drone Warfare”.

This work provides a framework to deploy reinforcement learning in robotics, identifies 5 axes of complexity, and outlines a roadmap for future drone warfare.

📑 https://t.co/uap5Q1ksdF

[Damien ERNST @DamienERNST1]

We had the pleasure to be invited today at the NATO Support and Procurement Agency in Luxembourg.

It was very interesting to discuss with them about the future of Artificial Intelligence for warfare and to present our work in this field.

[Damien ERNST @DamienERNST1]

Annual dinner of my research group.
I am so full of admiration for all these young clever people who want to push further the boundaries of knowledge for a better world.
Here is a link to all our scientific publications:
https://t.co/wXPURCIh2m

[Arthur @arthurlouette]

Wrapping up an inspiring first day at #EWRL with great company and a well-deserved beer! Huge thanks to @DamienERNST1 for this opportunity. The talks were incredible. Can't wait to see what the next days bring! #EWRL2024
@yanisgrts @SamyMokeddem
@LizePirenne @colsonlouis

[Damien ERNST @DamienERNST1]

[Thanks for sharing] We will have the immense pleasure to welcome the fantastic researcher @FlorianFelten1 for a research talk on Multi-Objective Reinforcement Learning in my research unit this Friday.

Please do not hesitate to come!

More information: https://t.co/vIipH7ZzdX

[Sergey Levine @svlevine]

Our new paper on using YouTube videos to learn language conditioned navigation is out! By leveraging pretrained models and video data mined from the web, we can get robots to better understand language instructions.

[Damien ERNST @DamienERNST1]

@Maxime44 You could also avoid jamming with directional antennas used in combination with drones acting as relays. That looks more clever to me and I think this technology is already used by Ukrainians on the battlefield.

[Damien ERNST @DamienERNST1]

Impressing.

But I believe this technology has three main weaknesses:
1. Very limited range
2. The fiber cable limits the mobility of the drone.
3. The fiber cable offers a huge vulnerability, especially for drone-on-drone combat.

[Peter Stone @PeterStone_TX]

10 years after DQN, what are deep RL’s impacts on robotics? Which robotic problems have seen the most thrilling real-world successes thanks to DRL? Where do we still need to push the boundaries, and how?

Our latest survey explores these questions! Read on for more details. 👇

[Damien ERNST @DamienERNST1]

#DroneWarfare

[Damien ERNST @DamienERNST1]

We can clearly see on the Ukrainian battlefield that drones are increasingly used to neutralize drones.

Soon, these drone dogfights will be powered by AI using computer vision as input.

[Pieter Abbeel @pabbeel]

Yes, 2024 is shaping up a big year for robotics!

Introducing @CovariantAI's RFM-1, which just like Sora can generate video, but RFM-1 does it for robotic interaction with the world.

But there is so much more it can do. RFM-1 is a multimodal any-to-any sequence model. RFM-1 tokenizes 5 modalities: video, keyframes, text, sensory readings, robot actions. Any-to-any means RFM-1 can handle any subset on the input and any subset on the output.

[Google DeepMind @GoogleDeepMind]

A common problem faced by researchers is finding and using information from scientific papers. 🔍

Gemini's capabilities mean it can accurately uncover knowledge within thousands of files including dense text & complex images.

How could this help deliver breakthroughs faster? ↓

[Corentin de Salle @CorentindeSalle]

Équipe de choc emmenée par l'un de nos plus grands scientifiques. Triste de ne pas être avec vous ce soir. A fortiori dans ce temple de la viande de nature à convertir au regime carné le végétalien le plus endurci. Vive la viande et vive l'atome !

[Damien ERNST @DamienERNST1]

Annual dinner of the exceptional Smart Grids group of the ULiège at the "Sabots d'Hélène", the legendary restaurant headed by Marc Carnevale.

If you want to know more about our research work focusing very much on AI and the energy transition =>  https://t.co/HlIu3dyxqo

[Xiaolong Wang @xiaolonw]

Introducing our CoRL work on Dynamic Handover. We humans often pass along objects, a baseball, a bottle of water, using throw and catch. 🫴⚾️

We now enable the robot hands to throw and catch different unseen objects using RL and Sim2Real transfer!

https://t.co/Xvn6F4jWVV

[sacha lewin @SachaLewin]

Thrilled to announce my first paper, "Dynamic NeRFs for Soccer Scenes", which was accepted at the MMSports 2023 workshop (@ ACM Multimedia)!

It features a part of my master's thesis work, in which I explore the use of dynamic NeRFs for the task of reconstructing soccer replays.

[Pascal Leroy @PaLeroy]

Warming up for #EWRL in Bruxelles! @GsprdLambrechts @MatthiasPirlet @arthurlouette @laurieboveroux