Pau Gargallo

@jon_barron Hans Rosling vibes on this one

An extrapolation from Grok Imagine. Not sure what it's imagining in terms of price elasticity among consumers of T2V models but I'm here for it.

@dhh Awesome! Thanks! Did you manage to turn off the led strip behind the screen? I failed at it and ended up putting black tape on it 😅

Next version of Omarchy has solved all the fiddly quirks and tweaks you need for the Asus G14/G16 series of laptops to work. Full support for brightness/volume/keyboard-backlighting controls, NVIDIA DGPU toggling, and audio mic fix. Such a great laptop with an incredible screen!

@DominiqueCAPaul @DominiqueCAPaul, i love following your adventures. Thanks for sharing them openly. We are building staer.ai to drive robot fleets. Would love to meet with Zurich based founders.

@DominiqueCAPaul 🙋‍♂️

Start-up events in Zurich are mostly lectures, panels and work driven. Almost no occasions to meet other builders in a casual setting. So I’m organising a simple founders’ cocktail evening this Friday. No agenda. Just drinks and food. A few spots left - who should join?

@DanielMiessler So cool! What is the voice to text tool you are using with CTRL+J at 6:30 in the video?

And here's the video describing it.

I built a @claudeai skill that it takes any input and converts it into different kinds of art for my site using Nanobanana 3.0. - Blog header art - Tech - Comics Available for free in our public Personal AI repo!

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀 One universal model enables SoTA for: 🔥 Mono Depth Estimation 🔥 Multi-View SfM 🔥 Multi-View Stereo 🔥 Depth Completion 🔥 Registration … and many more possibilities! – plus everything is metric 🎯 We release code for data processing, training, benchmarking & ablations – everything Apache 2.0! Details & Links 👇

@AjdDavison Anything with inputs too large to fit into memory?

What type of computation can only be done iteratively?

@iquilezles @DoItRealTime Can you get more phases by rotating the gears wrt each other?

@DoItRealTime Tried, but they clash, they are too close. Only have 0, 90, 180 and 270 degree phases available because of the axis grooves - we can't do something fancy like interleaving at 60 degrees.

We improvised a marble elevator with some lego technique and regular legos, for a duplos marble run we had around.

You know you are an old CV fart when you see SFM and think "Structure from Motion", but they mean "Spatial Foundation Models" Cool stuff: #Mission" target="_blank" rel="nofollow noopener">spaitial.ai/#Mission

Gemini + π0 = actually useful robots! (Similar to what @physical_int did with "Hi Robot") I can now verbally tell the robot that I'm building a red Lego wall or wooden tower, and it will infer the next steps by itself and pass me the necessary pieces, tools, or materials, ha! You can also just ask it to bring you things! The pipeline works as follows: - OpenAI Whisper (local) → speech to text - Gemini → makes sense of user requests, converts to robot tasks, bounding boxes, grasping points, etc. (System 2 thinking FTW!) - π0 → robotic actions The π0 was finetuned just for pick-and-place Lego bricks only, and it generalizes beautifully to all kinds of tasks. However, there's lots of room for improvement when it comes to grasping & accuracy. Things that could help: - Conditioning on grasping points - Better data collection (I'm not that great at teleop) - Lots more synthetic data and simulations

Thought about generating realistic 3D urban neighbourhoods from maps, dawn to dusk, rain or shine? Putting heavy snow on the streets of Barcelona? Or making Paris look like NYC? We built a Streetscapes system that does all these. See boyangdeng.com/streetscapes. (Showreel w/ 🔊 ↓)

@sellan_s @YouJiacheng Cool thanks! I couldn’t avoid seeing a sphere that was inside the curve in one drawing and outside in another and had to ask 😅

@sellan_s @YouJiacheng do you also use the normals during the reconstruction step to ensure that the surface is tangent to the spheres?

The wait is over 📢 MAST3R is out! DUSt3R+ dense local feature maps & metric depth - 1st in #MapFreeReloc leaderboard, can handle 1000s of images 😀 !! Blog: shorturl.at/9JTH2 Code: github.com/naver/mast3r Paper: arxiv.org/abs/2406.09756

@jon_barron Rage Against the Machine

The Quest v64 update brought two undocumented major new features: furniture recognition on Quest 3 and simultaneous hands & controllers in the home space: uploadvr.com/quest-v64-undo…

@karpathy I’ve only heard about Karpathy compile doing this

torch.compile is cool but LLM compile: takes your .py repo as string and outputs a brand new, custom, from scratch, minimal code repository directly running your network in highly optimized CUDA

Now available on Mapillary: Neural Radiance Fields (NeRFs)! 🎊 NeRFs allow for the transformation of a collection of 2D images into detailed, immersive 3D reconstructions. Read our blog post to learn more and see how you can get started with NeRFs: blog.mapillary.com/update/2024/03…

@toni_mateos Felicitats, cracks!

(1/2) We've won an Oscar!! Dolby Atmos has received the Academy Plaque for Scientific & Technical Achievements, the highest award short of an Oscar statuette, by the Academy of Motion Picture Arts & Science. youtu.be/h3IyGHbVlMw