🎉 Our paper "𝗙𝗿𝗼𝗺 𝗠𝗲𝗺𝗼𝗿𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝘁𝗼 𝗣𝗮𝗿𝗮𝗺𝗲𝘁𝗲𝗿 𝗜𝗻𝘁𝗲𝗿𝗳𝗲𝗿𝗲𝗻𝗰𝗲: 𝗛𝗼𝘄 𝗢𝘃𝗲𝗿𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗘𝘅𝗽𝗲𝗿𝘁𝘀 𝗛𝗮𝗿𝗺𝘀 𝗠𝗼𝗱𝗲𝗹 𝗠𝗲𝗿𝗴𝗶𝗻𝗴" was accepted at ICML 2026!
🔎 Do better expert models always lead to better merged models? Not necessarily!
📜Read the paper: https://t.co/aJN7Oi8Dw2
🧵 1/9
Agentic Scene Policies: General manipulation policy through agentic interactions with a 3D object map.
🌐 Website:https://t.co/YiaLDl7oNG
📄 Paper: https://t.co/qZmDIFwsxd
⏳Poster: Sunday Upper Level Room 29A-D (SpaVLE Workshop)
At #NeurIPS this week to present two projects! Come say hi if you’d like to chat about spatial AI, 3D perception, or the current state of robotics. Details 👇
Fun collaboration with Kumaraditya Gupta, Mahtab Sandhu, @velythyl, Francesco Argenziano, Kirsty Ellis and my advisor @duckietown_coo. Work done at @Mila_Quebec
🤖 Excited to share our recent work: Agentic Scene Policies!
General manipulation policy through agentic interactions with a 3D object map. Includes affordances, mobile queries and comparisons with VLAs!
📄 Paper: https://t.co/qZmDIFvUHF
🌐 Site: https://t.co/YiaLDl6QY8
Happy to share that we'll be presenting OpenLex3D at NeuRIPS in San Diego!
TLDR: New 3D segmentation and object retrieval benchmark for open-vocab 3D scene representations. Project page: https://t.co/yPiwOwasYt
I am very late to share this but StepMix has been accepted in the Journal of Statistical Software!
StepMix is a Python/R package for generalized mixture modeling with support for clustering and classification. Available here: https://t.co/vNNqkW9yVa.
Our paper OpenLex3D is accepted to NeurIPS 2025!
tldr; a new benchmark for open-vocabulary scene understanding methods.
Page: https://t.co/eZlwJGZBpI
With thanks to @SachMorin, Martin Büchner, @mmattamala, @kumaraditya_gup, Abhinav Valada, @duckietown_coo & @MauriceFallon
Full draft of the SLAM Handbook is now released and free online (https://t.co/gzJn4jweLh) Chapter 17 "Towards Open-World Spatial AI" written by myself, @SachMorin, Dominic Maggio, Martin Büchner, Cesar Cadena, Abhinav Valada, and @lucacarlone1. Great new resource for SLAM.
I am hiring another postdoc for my lab. Consider applying if you have #foundationalmodels, #robotics, or #reinforcementlearning skills. You will help create generalist real-world agents (robots) with a team of 20 working on these problems and overly competitive go-karting.
Pourquoi certains patients atteints de la COVID-19 s’en sortent-ils moins bien que d’autres? L’équipe de @SachMorin a utilisé l’IA pour étudier 300 patient·e·s hospitalisé·e·s et comprendre comment certains marqueurs spécifiques liés à leur réponse immunitaire et à l’infection influençaient l’évolution clinique. Lire l'article de blogue : https://t.co/xxNtzDiBvN
@he_randolph
We (@dineshjayaraman , @akrishna42 , and I) recently went on the Economist podcast to discuss DrEureka (https://t.co/8A5PdZrUGw) and other recent works from our lab as well as trends on robot foundation models! Give it a listen if you are interested!
our work delving into the interferon paradox is now out in @NatureComms!
couldn’t have asked for better co-authors on this one, congrats all 🥰 @ERatnasingham@SachMorin @mhultstrom @LB_Barreiro
https://t.co/UU7D7dVztS