Part 2 of SLAM handbook is out for public comments! let us know what you think :-) Issue tracker on GitHub awaits! Link in comments.

You start making progress with your life once you realize that there is no perfect relationship, no perfect draft, no perfect investment, no perfect house, no perfect diet, no perfect city, no perfect job, no perfect choice, no perfect life. You try, you fail, you "waste" time,

A free PDF of my book "Rollout, Policy Iteration, and #ReinforcementLearning " has been posted at my web site web.mit.edu/dimitrib/www/d… An extensive research account on rollout algorithms, including multiagent rollout, and the connection with Newton's method

Congratulations to two Nottingham Trent University researchers, Dr Martina Gabrielli and Dr Yuri Kawaguchi, who have been awarded prestigious fellowships from the Biotechnology and Biological Sciences Research Council - the first time NTU has received such fellowships. 🎉

#llm s in #ros2

Want to recognize a song from just a few seconds of distorted audio? Use Constellation Maps. The math is brilliantly simple. With just a handful of bytes; discarding 99% of the waveform, you can recognize a unique fingerprint across hundreds of millions of tracks.

You know all those arguments that LLMs think like humans? Turns out it's not true. 🧠 In our paper "From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning" we test it by checking if LLMs form concepts the same way humans do Yann LeCun Chen Shani Dan Jurafsky

Smart people are quiet. Strong people are calm. Wealthy people are private. Being angry and loud is nothing to be proud of.

Our next-gen interactive video model is shaping up to be so exciting. Check out these early outputs. AI-imagined video that you can play like a game feels like a totally new form of media. The YouTube of interactive video must be built to enjoy it 🥰

Thrilled to be speaking at the 1st #ROSConUK in September! I'll be sharing updates from the Aerial Robotics Community Interest Group (with Ramon Roche 🚀 !) & giving a lightning talk on the big robot simulator list I'm maintaining. See you in Edinburgh! 🚁 roscon.org.uk/2025/#attend

Excited to make our best AI tools free for college students in the US + other select countries for a year - and to provide $1B in funding for education + research, including free AI and career training for every college student in America.

This is really exciting and impressive, and this stuff is in my area of mathematics research (convex optimization). I have a nuanced take. 🧵 (1/9)

It’s time to get rid of frame rates. In weird corners of the internet, researchers and standards committees discuss frameless video containers. Sensor data as a continuous function, down-sampled to any frame rate you want. Here's what it'll look like in 10 years:

@ UKCI 2025 @ Edinburgh Napier University

neuralsvcd.github.io NeuralSVCD for Efficient Swept Volume Collision Detection NN-accelerated collision detection, useful for planning

Goosebumps! Sri Lanka’s 🇱🇰 anthem on the top of the podium as Yevan David wins 🏆 Race 2 of EuroFormula Open 2025 (Round 6) at the Red Bull Ring. Proud moment for the nation🇱🇰💪! #Motorsport #SriLanka #EuroFormulaOpen #LKA

beginner robotics is learning ros + sims. advanced robotics is dealing with reality. what that means: state estimation → ekf, ukf, factor graphs. noise never lies. planning under uncertainty → p(o|s,a). real robots don’t get perfect info. optimal control → lqr, mpc.

🚨Announcing the World Modeling Workshop 2026 🚨 📅 When: Feb 4–6, 2026 📍Where: Mila (Montréal) + Online (free) 💡 What: Keynotes, Methods Deep Dive, and Tutorials 🌐 world-model-mila.github.io ✉️ [email protected] 🧵 Details below:

Correct! Just as a reminder: this is what a Transformer found after looking at 10M solar systems

Fei-Fei Li says language models are extremely limited. This Google DeepMind paper makes almost the same point, just in the world of video. The models are just very advanced pattern matchers. They can recreate what looks like reality because they’ve seen so much data, but they