It was a blast to visit the @cbehav.bsky.social ! I am impressed by their concentration of talent and creativity. I am also grateful for the warm hospitality of @swarmdynamics.bsky.social and @joefresna.bsky.social, who made this day even more special! Let's write a paper already :-)

Today we’re thrilled to welcome Carlo Pinciroli @carlo.pinciroli.net from the Worcester Polytechnic Institute for our next CASCB Talk! Join us at 12:00 to explore heterogeneity in robot swarms! 📍 ZT 702 & online www.exc.uni-konstanz.de/collective-b...

Very happy to welcome a good friend @carlo.pinciroli.net in the wonderful Konstanz to speak about cool science for a couple of days! Hopefully, these meetings will trigger some fun collaboration!

We are excited to announce that the Fifteenth International Conference on Swarm Intelligence (ANTS 2026) will be taking place on June 8-10, 2026 in Darmstadt, Germany. 📅 Submissions: Nov 10, 2025 📅 Notification: Jan 30, 2026 📅 Conference: June 8-10, 2026 🌐 ants2026.org

Best week ever, with Josh Bloom defending his PhD dissertation titled "Global State Prediction for Multi-Agent Reinforcement Learning in Collective Transport." Congratulations! Many thanks to Dr. Nicola Bezzo, Dr. Kevin Leahy, and Dr. Guanrui Li for your time and detailed feedback!

More great news! Stephen Powers defended his PhD dissertation, "Symbolic Model Extraction in Homogeneous Heterogeneous Swarms." Many thanks to Dr. Eliseo Ferrante, Dr. Kevin Leahy, and Prof. Bill Michalson, for your time and insightful feedback!

Great news! @ashay-aswale.bsky.social defended his PhD dissertation "Simultaneous Task Scheduling and Coalition Formation in Multi-robot Systems Using Centralized and Decentralized Methods." Many thanks to Dr. Emanuele Garone, Dr. Kevin Leahy and Dr. Guanrui Li, for your time and great feedback!

Vim is the original escape room

so they're mycoblogging

Oh now that's something

I'm proud to announce that @khaiyichin.bsky.social defended his PhD dissertation titled "Sensing Through Faults: Collective Perception by Imperfect Robot Swarms." Many thanks to @swarmdynamics.bsky.social, Dr. Kevin Leahy and Dr. Nitin Sanket, for your time and your thoughtful feedback!

More and more, BlueSky is where academics share their findings.

Robotic insects? Sound useful but still very creepy. @ericowens.bsky.social www.livescience.com/technology/r...

We're excited to announce the first Evolving Self-organisation workshop at GECCO 2025! Submission deadline: March 26, 2025 More information: evolving-self-organisation-workshop.github.io

This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235

3/ AI breakthroughs like AlphaFold wouldn’t be possible without decades of work on datasets. e.g., AlphaFold was trained on protein structures from the Protein Data Bank (PDB), which took 50+ years and ~$20 *billion* to create. This is the kind of foundational effort AI needs.

In recent decades, wildland fires have been enabled by many factors, including the legacy of fire suppression, human settlement and distribution patterns, other management actions, and even natural climate variability. 1/

I have a draft of my introduction to cooperative multi-agent reinforcement learning on arxiv. Check it out and let me know any feedback you have. The plan is to polish and extend the material into a more comprehensive text with Frans Oliehoek. arxiv.org/abs/2405.06161

Why are evolved networks (such as gene and metabolic webs) different from engineering designs? One lesson is provided by evolved electronic circuits, as shown in this @sciam.bsky.social paper by John Koza jstor.org/stable/pdf/2...

A rare actual good news story: bees – both honey bees and wild bees – seem to be doing better in the UK. Bee-friendly planting, less pesticide use and an uptick in beekeeping are all having results 🐝 🎉 inews.co.uk/inews-lifest...

Astonishing how many RL bottlenecks are resolved simply by “make simulator go fast”. What if we had prioritized engineering over algorithms years ago?

1/ Okay, one thing that has been revealed to me from the replies to this is that many people don't know (or refuse to recognize) the following fact: The unts in ANN are actually not a terrible approximation of how real neurons work! A tiny 🧵. 🧠📈 #NeuroAI #MLSky

Pretty much my inner voice as I write proposals

In today's lecture in my nonlinear dynamics and chaos course, I tried to give intuition for where chaos comes from. It's caused by repeated stretching and folding of phase space.

Nothing cooler than emulating nature very well: "Bird-inspired drone can jump for take-off" [via EPFL News] 🧪🤖🐦 "EPFL researchers have built a drone that can #walk, #hop, and #jump into #flight with the aid of birdlike legs..." actu.epfl.ch/news/bird-in... #robotics #bird #drone #mechatronics

#swarm #robotics

An updated intro to reinforcement learning by Kevin Murphy: arxiv.org/abs/2412.05265! Like their books, it covers a lot and is quite up to date with modern approaches. It also is pretty unique in coverage, I don't think a lot of this is synthesized anywhere else yet

📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social! What you get, why you should be interested and more, all below in a short 🧵👇

Three must read papers for PhD students. #scisky #PhD #science #research #academicsky 1. The importance of stupidity in scientific research Open Access journals.biologists.com/jcs/article/...

📊 #dataviz A couple of years old, but still worth reading-- The Science of Visual Data Communication: What Works A very thorough review of ideas and evidence by @SteveFranconeri, @LacePadill and others. journals.sagepub.com/doi/epub/10....

Two stages of writing: 1) This shouldn't take too long 2) Oh no

My 8 year old niece explained cryptocurrency better than anyone else I've ever heard: "if cryptocurrency had real value, the people selling it to you wouldn't be accepting bank money." The kids are going to be alright.

Only by Feb 2012 had Twitter's volume crossed 100k tweets in a month for the first time. It took until April of 2013 for monthly tweet volumes to reach over 200k. And Jan 2014 was the first monthly total over 300k tweets about research. Public Bluesky is only "February 2024 years old" and has 395k.

There are already many articles for which there is more attention on Bluesky than on other comparable micro-blogging sites, meaning the academic community and the general public have clearly adopted Bluesky as one of its core places to disseminate and discuss new research. A Place of Joy.

Like 130,000 others, I made a starter pack. This one is people working on or with evolutionary computation in its many forms: genetic algorithms, genetic programming, evolution strategies. If you like to be added, or suggest someone else, message me or reply to this post.

📢NEW: 'Open' AI systems aren't open. The vague term, combined w frothy AI hype is (mis)shaping policy & practice, assuming 'open source' AI democratizes access & addresses power concentration. It doesn't. @smw.bsky.social, @davidthewid.bsky.social & I correct the record👇 nature.com/articles/s41...

No. Effective governance is also a strong chance, and indeed these two powers (the open source community & governments) collude in the EU. But we need to work well with the rest of the world to stand up to the US and China both. Fortunately, US+CN < 40% global GDP now so this is possible, if hard.

3D Gaussian Splatting is awesome! BUT, the 3D Gaussian primitives often have difficulty reconstructing fine appearance details. 😩 Meet Textured Gaussians! ✋ Our RGBA Textured Gaussians enhance 3D scene appearance modeling. Learn more at textured-gaussians.github.io

#Multi-robot systems on the #Moon are about to be a reality. One of the coolest projects possible. So many hard and interesting problems to solve! #robotics #space www.youtube.com/watch?v=jePS...

readingList.push(this)

This thread is equal parts inspiring (perseverance!) and educational (it's just how impactful work is done). Also, the final comments apply well beyond the Netherlands.

𝗦𝗲𝗹𝗳-𝗢𝗿𝗴𝗮𝗻𝗶𝘇𝗶𝗻𝗴 𝗦𝘆𝘀𝘁𝗲𝗺𝘀: 𝗪𝗵𝗮𝘁, 𝗛𝗼𝘄, 𝗮𝗻𝗱 𝗪𝗵𝘆? Good intro by Carlos Gershenson #complexity www.preprints.org/manuscript/2...

#Robotics packs Biggest: bsky.app/starter-pack... (full) Open source: bsky.app/starter-pack... Women: bsky.app/starter-pack... Vision: bsky.app/starter-pack... Distributed: bsky.app/starter-pack... AI: go.bsky.app/DfAoaJ1 More: bsky.app/profile/scot...

Death of Star vs Birth of Cell

Very interesting paper, not only for neuroscientists

Thank you to the @neuripsconf.bsky.social for this recognition of the Generative Adversarial Nets paper published ten years ago with @ian-goodfellow.bsky.social, Jean Pouget-Abadie, @memimo.bsky.social, Bing Xu, David Warde-Farley, Sherjil Ozair and Aaron Courville. blog.neurips.cc/2024/11/27/a...

In this thread, I’ll be assessing a variety of humanoid robots from the past 30 years over the coming weeks. Points will be awarded for anthropomorphism, practicality, and—most importantly—the silliness of their acronyms.

Cool automatic authoring of interactive, simulation based diagrams for textbooks. Augmented Physics: Creating Interactive and Embedded Physics Simulations from Static Textbook Diagrams Video: www.youtube.com/watch?v=HUgY... Short explainer: tinyurl.com/2wfs74u3 Paper: arxiv.org/abs/2405.18614

Check out the Distributed Robotics Systems Starter Pack: It features researchers exploring swarm robotics, multi-robot systems, modular robots, and more! Know someone who should be included? Suggest yourself or others in the replies! 🐝🤖 #Robotics #SwarmRobotics #DistributedRobotics #Swarm