Image created with GPT Image 1. Image prompt: interlaced diagonal rainbow bars, Music Complete polychrome palette, minimalist graphic design inspired by New Order’s ‘Music Complete’, metaphor for spatial computing portals, flat color, subtle texture, 1980s Saville typography style
Check out this insanely detailed 3D scan of the Great Pyramids of Giza by Geomatex. You can literally zoom in and read the tablet in front of the Great Sphinx. Drone photogrammetry w/ high res textures is perfect for immortalizing these landmarks. https://x.com/bilawalsidhu/status/1921405376727068784
🎥 @higgsfield_ai Hollywood-Level Videos from a Single Image Uses 50+ pro-level camera moves — from bullet time to crash zooms, robo arms, and FPV chases — to turn static images into cinematic videos Some beutiful examples.. 🧵 1/n – 3D Rotation The subject or product spins https://x.com/rohanpaul_ai/status/1922241875089543546
Not bad from GPT-4.1: “”create something I can paste into p5js that will startle me with its cleverness in creating something that invokes the control panel of a starship in the distant future”” First go, no errors. https://x.com/emollick/status/1922749136996114771
Elon just dropped a new Optimus demo – trained with sim-to-real reinforcement learning. Video speed: 1X https://x.com/TheHumanoidHub/status/1922090337364848942
Roblox is scaling 3D world creation for ~100M daily active users. In this full episode, I sit down with Roblox’s VP of AI, Anupam Singh to break down: – Cube AI (their new generative model) – LLMs + 4D world-building – Vibe coding & in-experience creation Timestamps: 00:00 https://x.com/bilawalsidhu/status/1922306590377705781
Boston Dynamics’ robot-behavior team lead highlights three core initiatives aimed at advancing Atlas’s dexterity: ⦿ Reinforcement learning in simulation ⦿ Whole-body teleoperation to collect data for imitation learning ⦿ Tactile sensing grippers https://x.com/TheHumanoidHub/status/1921974665678823770
I built an 8-bit retro dashboard in 10 minutes using: – @nextjs – @shadcn – @v0 – 8bitcn ⚔️ Watch the full video below 👇 https://x.com/theorcdev/status/1915716377194660120
Love these old meets new vfx workflows 1. extract a still of the object you want to augment 2. use image-to-3d to make a 3d model of the object 3. use that 3d geometry for classical object tracking Then you can go wild with complete control https://x.com/bilawalsidhu/status/1921776024364228810
🎥 NFTOTEM — concept animation, built with patience and through @v0 prompts. It took time, but the magic happened. ✨ https://x.com/antongridz/status/1914767141653581893
TeGA: Texture Space Gaussian Avatars for High-Resolution DynamicHead Modeling https://syntec-research.github.io/UVGA/
Lego + AI = this https://x.com/fdaudens/status/1922008150133059883
Introducing AI Alive: Bringing Your Photos to Life on TikTok Stories – Newsroom | TikTok https://newsroom.tiktok.com/en-us/introducing-tiktok-ai-alive
It’s fun to see all the new uses cases coming up with this latest References update. Feels like Christmas but every day. Here is zero-shot novel view synthesis for people and characters, works straight out of the box. https://x.com/c_valenzuelab/status/1922656353354412332
Introducing Meta 3D AssetGen 2.0: A new foundation model for 3D content creation | Meta Horizon OS Developers https://developers.meta.com/horizon/blog/AssetGen2
Meta AI launched Locate 3D, an AI for 3D object localization Particularly useful in robotics, it can help humanoids and other systems understand and interact more naturally with their surroundings Model, data, and code are all available on HF https://x.com/rowancheung/status/1921815727197012383
Introducing Meta Locate 3D: a model for accurate object localization in 3D environments. Learn how Meta Locate 3D can help robots accurately understand their surroundings and interact more naturally with humans. You can download the model and dataset, read our research paper, https://x.com/AIatMeta/status/1920516490182471818
UC Berkeley researchers announced VideoMimic, a real-to-sim-to-real pipeline that trains robots with mobile videos It mines videos, reconstructs the humans and the environment, and produces policies for humanoids, enabling skills like climbing stairs https://x.com/adcock_brett/status/1921597176028733566
Going to ICRA next week in Atlanta!! We are on a mission to build the most cracked team on humanoid robotics. Hiring the best talents on the research frontier of VLA, world models, RL, and simulation! DM or email me for meetup! linxif@nvidia.com https://x.com/DrJimFan/status/1922723389942194522
Optimus Engineer Lead: For the dancing demos, the Optimus team had to make significant improvements in simulation models, domain randomization, and other techniques that transfer directly to practical tasks like walking and full-body control. https://x.com/TheHumanoidHub/status/1922469257176039678
🤖Introducing TWIST: Teleoperated Whole-Body Imitation System. We develop a humanoid teleoperation system to enable coordinated, versatile, whole-body movements, using a single neural network. This is our first step toward general-purpose robots. 🌐 https://x.com/ZeYanjie/status/1919779536461561860
New Optimus video is out! It’s a real robot – damn! https://x.com/TheHumanoidHub/status/1922458479492555087
Elon: Multiple Optimus robots walk around the office 24/7 with no one watching over them, charging themselves as needed. https://x.com/TheHumanoidHub/status/1922548079418376531
Jim Fan: Neural World Models are going to scale exponentially with compute and will enable the next generation of robotics systems. https://x.com/TheHumanoidHub/status/1920305929377005658
Generating Physically Stable and Buildable LEGO Designs from Text https://avalovelace1.github.io/LegoGPT/
