For 41 years, to find shortest paths in a... graph, the Dijkstra’s algorithm, was seen as the best possible way. Not any longer: Now a team from Tsinghua University has beaten it. They created the first faster algorithm for directed shortest paths since 1984. • Faster than Dijkstra on large sparse graphs • Works with real, non-negative edge weights • Proves that sorting is not the main bottleneck anymore Shortest-path algorithms power maps, GPS, logistics, networking, and robotics. This result shows that even the most “finished” algorithms can still be improved. Thanks for sharing, Md Ismail Šojal 🕷️! 📍 Paper: —— Weekly robotics and AI insights. Subscribe free:show more

dog follows pointer + avoids collisions with no dependencies... - builds the page as a graph, more subdivisions towards the text for perf - dijkstra shortest pathshow more

Dijkstra’s algorithm doesn’t just tell you the fastest route... to one destination. Instead, it gives you an ordered list of travel times from your current location to every other point that you might want to visit — a solution to what researchers call the single-source shortest-paths problem.show more

Oldies but goldies: L.E. Dubins, On Curves of Minimal... Length with a Constraint on Average Curvature, and with Prescribed Initial and Terminal Positions and Tangents, 1957. Dubins paths are the shortest path for cars that can only move forward.show more

🚀 Imitating shortest paths in simulation enables effective navigation... and manipulation in the real world. Our findings fly in the face of conventional wisdom! This is a big joint effort from PRIOR Ai2 (6 first authors!).show more

Its not every day you wake up to find... that the Pope has made your lifes work the central focus of his papacy: “Disarming AI means freeing it from the mentality of “armed” competition [..] This entails a race for ever more powerful algorithms and larger datasets, driven by the desire to secure geopolitical or commercial dominance." - POPE LEO XIV, May 2026 Here, “disarmed” means “neutralised” in the sense that this should not be a differentiator The Innovation Game (TIG) was created to keep data and algorithms open, in order to prevent monopolistic control It's not just an aspiration, it's an economic mechanism that makes open data and open algorithms the rational economic choice • All algorithms are published openly by TIG • If you are willing to make the data you process with an algorithm open, you can use it free-of-charge • Alternatively, if you would like to keep this data private, there is a fee to pay for using the algorithm • All fees are used to fund more open innovation Its an elegant, global, self-reinforcing engine The logical end point of monopoly is that innovation stops We cannot allow that to happen Pope Leo XIV I would be grateful for your thoughts on The Innovation Gameshow more

Palletizing in the real world! 📦🤖 How do you... stack 65 unique SKUs on a pallet when they arrive in random order? Here’s how an on-the-fly algorithm solved it in a real logistics use case with only a single-digit buffer. Every placement was checked for stability, not just for itself, but for every other box it touched. The result? A rock-solid 2.05 m (6.5 ft) pallet. Robotics in logistics keeps improving. Hardware matters, but without smart software your robots won’t know what to do and you’ll waste money and time. Credit: Progressive Roboticsshow more

XYZ: Let’s build a humanoid company to save humanity... from the labour shortage Meanwhile: —- Weekly robotics and AI insights. Subscribe free:show more

AI in robotics gets all the attention right now,... but sometimes the most interesting work is very practical. Viet built a small vision system that counts potatoes on a conveyor belt. No giant dataset. No huge model. Just a clear problem and a smart setup. He used Ultralytics’ ObjectCounter, trained a tiny YOLO11 nano model, and because there was no potato dataset, he annotated a single frame with SAM 2 and trained from that. One frame. Still works across the whole video. It is a good reminder that useful AI in industry often looks like this. Focused. Lightweight. Solves a real task. If you work in manufacturing or robotics, these small systems are usually the fastest wins. They save time, reduce errors, and do not need massive infrastructure. Nice work, Viet. His projects: —- Weekly robotics and AI insights. Subscribe free:show more

In Paralives, you can set Parafolks with different heights,... with 1.96m (6'4") being the tallest and 1.49m (4'10") being the shortest for adult. Here's what it looks like when the shortest adult kisses with the tallest 🤯show more

Multi-axis 3D printing with curved layers! 🖨️ Researchers from... the The University of Manchester introduced a neural network-based computational pipeline as a representation-agnostic slicer for multi-axis 3D printing. Traditional 3D printing works like stacking pancakes, flat layers on top of each other. 🥞 This often requires temporary support structures that get thrown away after printing, wastes material, and creates weaker parts. Multi-axis 3D printing can print along curved paths that follow the object's natural shape. This eliminates support structures and makes stronger parts. But figuring out these curved paths is mathematically complex, you need to avoid collisions, respect what the printer can physically do, and optimize for strength. The neural network solves this automatically. It learns to create a "field" around the object, then extracts curved printing paths from this field. Because the entire process is differentiable (translation for non-math specialists, meaning you can optimize it end-to-end), the AI can directly optimize for manufacturing goals like "no support structures needed" and "make it as strong as possible." Here's the project: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →show more

Most imitation learning policies break when the camera moves... or the robot changes. NOT THIS ONE 👇 [📍 Bookmark for later ] A new 3D scene representation encoder, tackles this by enabling zero-shot generalization to unseen embodiments and viewpoints… And it works with any IL algorithm. The trick? •Use a 2D foundation model to extract semantic features •Lift them into 3D space for localization (not semantics) •Condition the IL policy on this spatially grounded vector Across 93 simulated and 6 real tasks, Adapt3R: ✅ Maintains IL performance on LIBERO & MimicGen benchmarks ✅ Outperforms DP3 and 3D Diffuser Actor in most settings ✅ Holds >80% success on LIBERO even with large camera rotations Thanks for sharing this, Animesh Garg & Albert Wilcox! 📍Paper: Website: Code:show more

NEW CHALLENGE ANNOUNCEMENT Announcing the Energy Arbitrage designed in... collaboration with CryptoEconLab It's been on testnet for over a month and live on mainnet next week! So what is energy arbitrage and why does it matter? AI is eating electricity faster than grids can supply it The algorithms that decide how grid-scale batteries charge and discharge are becoming some of the most consequential algorithms on Earth, and until today they've been locked behind closed doors.show more

🐈‍⬛ yesterday i got to see all the members... together for the first time in a while when I looked turns out I had the shortest hair Ryujin hair has grown out a lot. I was thinking, “should I cut mine even shorter? i think i will can’t believe yeji have the shortest hair now 😆show more

Most humanoid projects talk about real work. Very few... last an hour on a real line. This week I saw a case that matters for anyone building robots, perception, or physical AI. Kinisi deployed its first mobile manipulation system into a live recycling facility. Not a demo. Not a staged test. A real production line with real output pressure. Why this matters if you want robotics to deliver real value on your floor: • Handles mixed glass with random poses and no fixed fixtures. • Runs real grasp selection under noise, vibration and production variability. • Maintains throughput while avoiding breakage on a delicate material. • Shows mobile manipulation doing actual shift work instead of controlled lab runs. Kinisi published a video that shows what the robot sees and how sensor data turns into action. This is the part most teams struggle to explain to customers, so the educational angle is useful for anyone working on adoption. On top of this, the team signed a pilot with a global automotive manufacturer to explore humanoid use cases in production. The direction is clear. Wheeled mobility (not legs!) plus strong perception seems to be shaping a large part of industrial humanoids right now. I know Brennand from earlier conversations and from our podcast session, and I am always glad to see European teams push the category forward. Wishing the Kinisi team continued success. —- Weekly robotics and AI insights. Subscribe free:show more

Learn How To Build a Gemini-Powered Robotics Simulator in... the Browser with MuJoCo WASM. MuJoCo (WebAssembly) + Three.js + Gemini ER Thanks for sharing, Omar Sanseviero! 📍Tutorial: Demo: —— if it matters in AI or Robotics you'll see it here first:show more

Finished this one faster than I thought! The full... version is on my site right now. If you can’t support the site...it will be released here in July. Also, consider liking and sharing my vids as a free way to support my work. Having Ashley (AI Model) hulk out and level a city was toooooooo fun lol.show more

100x faster alternative to Pandas! (It can even beat... GPU dataframe libraries) While Pandas is the most popular DataFrame library, it has some major limitations: - Pandas only uses a single CPU core. - It often creates bulky DataFrames - Its eager (immediate) execution prevents global optimization Introducing FireDucks a highly optimized, drop-in replacement for Pandas. Just change one line of code and you're good to go: ↳ import fireducks.pandas as pd The video below shows a comparison of FireDucks with cuDF—a GPU DataFrame library. In this case, it's even faster than cuDF. That said, the query in the video has chaining operations and it uses all columns. By manually optimizing and working only with the necessary columns, the run-time decreased to: - Pandas: 14 seconds (down from 48 seconds) - FireDucks: 0.8 seconds (unchanged) [SIMILAR] - cuDF: 0.9 seconds (down from 2.6 seconds) This demonstrates that FireDucks' compiler automatically performs the same optimizations that you would need to explicitly implement in cuDF and Pandas. Most importantly, the optimization does not affect the final result. I've shared a link to the Colab notebook in the next tweet. _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials in AI and Machine Learning.show more

Shortest path is not always the fastest path. Literally... proven by physics. Metaphorically proven by life.show more

Here is a showcase of two plugins that will... be available in our next client update. Tile Packs & Shortest path! Shortest path features a breadcrumb trail that we are sure is familiar to some of you!show more