🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Happy to share that we won the #ICRA2023 unfolding and folding cloth competition! Congrats to IDLab #AIRO members Remko Proesmans Victor-Louis De Gusseme Thomas Lips & Andreas Verleysen Thanks IRI-Institut de Robòtica i Informàtica Industrial for organising this competition!

Happy to share that my latest paper "Learned Thresholds Token Merging and Pruning for Vision Transformers" is now published by Transactions on Machine Learning Research. Paper: openreview.net/forum?id=WYKTC… GitHub: github.com/Mxbonn/ltmp Website: maxim.bonnaerens.com/publication/lt…

#GPT4 and real-time video feed for enhanced context awareness in social robots! 🤖👀 Explore the code and results in my latest post (and paper!): dev.to/giubots/implem… #Furhat Furhat Robotics #LLM #HRI #HumanRobotInteraction #UGent #DEVCommunity

This semester the IDLab #AIRO developed a new course on #IntelligentRobotManipulation 🤖🤖It took an effort from both the students and us, but I’m happy with the result of our last practical session (today). Faculty of Engineering and Architecture UGent 1/3

Working on #robotics 🤖manipulation of #cloth🧶? Participate in our robot competition by identifying grasp point localisation on hanging cloth items, and test them live at IEEE ICRA #ICRA2024 Japan! 🛎️Subscribe now: airo.ugent.be/cloth_competit… euROBIN IDLab

Happy to share that our work was accepted as spotlight at ICLR! I hope to see many other people working on SDEs and/or video models in Vienna🇦🇹

OLMo is here! And it’s 100% open. It’s a state-of-the-art LLM and we are releasing it with all pre-training data and code. Let’s get to work on understanding the science behind LLMs. Learn more about the framework and how to access it here: blog.allenai.org/olmo-open-lang…

Totally impressed by the Google Scholar PDF Reader Browser Extension! It's completely transformed how I check references on the fly.📚 #GoogleScholar 🔗 scholar.googleblog.com/2024/03/superc…

After two years, it is my pleasure to introduce “DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset” DROID is the most diverse robotic interaction dataset ever released, including 385 hours of data collected across 564 diverse scenes in real-world households and offices

The IEEE ICRA IDLab #AIRO cloth folding competition going very well under the supervision of Victor-Louis De Gusseme Best of session Wednesday 16h00. More details on airo.ugent.be/cloth_competit… Thanks for the support euROBIN Faculty of Engineering and Architecture UGent imec in Vlaanderen Universal Robots

⭐ The first foundational model available on LeRobot ⭐ Pi0 is the most advanced Vision Language Action model. It takes natural language commands as input and directly output autonomous behavior. It was trained by Physical Intelligence and ported to pytorch by Pablo Montalvo 👇🧵

I'd like to live in a world where all countries & organizations, big or small, can train their own AI, instead of just a few of the richest & biggest ones. This is IMO one of the most important topics ever and will shape the future of the world. That's why I'm super proud when

wrote a new post, the gentle singularity. realized it may be the last one like this i write with no AI help at all. (proud to have written "From a relativistic perspective, the singularity happens bit by bit, and the merge happens slowly" the old-fashioned way)

I will be presenting our work on using text-to-image diffusion models for synthetic data generation at the #CVPR2025 syndata4CV workshop later today Feel free to come to our poster if you want to chat about synthetic data! ( poster #229, 1 pm)

A new chapter in robotics is about to begin. 🤖 The next generation of 4NE1—our cognitive humanoid robot—is ready and we're bringing it to the stage at automatica 2025 in Munich. 📍 Hall B4, Booth 319 🕑 Tuesday, June 24, at 11 AM This is an event you won't want to miss!

Amid all the noise and rapid pace in the field, I really appreciated Russ Tedrake’s talk on their LBM work and the rigorous evaluations that go beyond flashy demos—some papers these days don’t even include error bars. The talk offered valuable insights on avoiding reinvention.

Totally agree! TRI is currently the gold standard in robotic manipulation research imo Highly recommend watching this talk

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the