Image created with Ideogram v3. Image prompt: Late‑90s boy‑band cover “Virtu‑Boys – Beyond Reality”: members wearing translucent visor headsets reaching toward viewer; grid floor fades into pixelated horizon; color‑blocked windbreakers in magenta‑cyan; chrome curved logo.
“As part of its Spring 2025 update, Yelp will test an AI-powered feature that lets restaurants and businesses handle customer calls using virtual agents. This will help businesses operate even when their support staff is busy or unavailable https://x.com/rowancheung/status/1917473898808967498
“trackers v2.0.0 is out combo object detectors from top model libraries with multi-object tracker of your choice for now we support SORT and DeepSORT; more trackers coming soon link: https://x.com/skalskip92/status/1915439480594485363
“Here, the fly shows accurate movement along complex natural flight trajectories. Watch how it’s instructed to follow a real path marked by the blue dots. 🔵🪰🔵 https://x.com/GoogleDeepMind/status/1915077093819380209
“Today we are releasing Gen-4 References to all paid plans. Now anyone can generate consistent characters, locations and more. With References, you can use photos, generated images, 3D models or selfies to place yourself or others into any scene you can imagine. More examples https://x.com/runwayml/status/1917628723903463526
“DeepMind built an AI that replicates how a fruit fly walks, flies, and behaves — using MuJoCo, its open physics simulator The work will help scientists understand what drives specific behaviors in the fly, finding links that labs can’t always measure https://x.com/rowancheung/status/1915288472513872024
Teaching LLMs how to solid model https://willpatrick.xyz/technology/2025/04/23/teaching-llms-how-to-solid-model.html
“If your AR glasses don’t make you look like a 90s action villain, are they even worth buying? https://x.com/bilawalsidhu/status/1916266941242540497
“Night vision and thermal fusion is incredibly powerful. And these are just the cheaper clip-on systems. Imagine what IVAS could do w/ sensor fusion + augmented reality. https://x.com/bilawalsidhu/status/1916480759314993282
Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction https://simongiebenhain.github.io/pixel3dmm/
“I had an exercise in my class where students had to invent a business using a magic 3D printer that could make any object out of plastic 1 ft x 1ft x 1ft for $1 in a minute. Over thousands of students the vast majority clustered around a few ideas The lesson applies to AI, too. https://x.com/emollick/status/1915600033052819521
“Hey @amasad, you’ve helped a 9 year old software engineer – building 3D worlds and interactive games. My son went to an escape room. When he came back he wanted to buy the game. I said let’s build it. And we went cranking. We built this using AI + Replit. It was so much fun. https://x.com/tashfees/status/1912309083736273276
“Built a full-on app animation in @cursor_ai using our real components. Pasted it into @v0.dev, recreated it, and asked for a version compatible with @remotion_dev (Because it renders React frame-by-frame into a real video file—so you can actually export it vs. screen record) https://x.com/virtualhorizonn/status/1911911588396937676
“Watch Gemini 2.5 Pro vibe-code a 3D cake visualizer 🎂 Using Three.js, it builds custom animations, UI controls, updates the visuals based on feedback – and even gives price estimates. ↓ https://x.com/GoogleDeepMind/status/1917221723834827196
“Had the pleasure of speaking at the Harvard Graduate School of Design for the Harvard XR event – an incredible gathering of minds shaping the future of AR/VR, from the VFX visionary behind Iron Man’s JARVIS to the builders at the likes of Meta and Samsung bringing that world to https://x.com/bilawalsidhu/status/1915450942150898079
“Imagine AI turning a photo into a playable 3D world. 🌍 On @60Minutes, our Research Scientist @jparkerholder joined CEO @DemisHassabis to demo Genie 2’s image-to-3D world creation – exploring the possibilities it could bring to how AI learns. ↓ https://x.com/GoogleDeepMind/status/1916799144385011779
Hugging Face releases a 3D-printed robotic arm starting at $100 | TechCrunch https://techcrunch.com/2025/04/28/hugging-face-releases-a-3d-printed-robotic-arm-starting-at-100/
“Generative AI is cool and all, but SDF modeling just hits different. Non-destructive shaping, blending and boolean modeling on an iPad using Uniform 1.4 https://x.com/bilawalsidhu/status/1915901879147544815
“Boston Dynamics collaborated with NVIDIA to demonstrate DextrAH-RGB, a workflow for dexterous grasping from stereo RGB input. The end-to-end policy for Atlas robot, trained entirely in NVIDIA Isaac Lab, transfers zero-shot from simulation to the real robot. https://x.com/TheHumanoidHub/status/1915863695948939570
“NYU researchers introduced RUKA, an open‑source, tendon‑driven, and 3D-printable robotic hand with 15 DOF It can operate for 20 hrs straight and successfully perform 31 out of 33 grasps in a standard grasp taxonomy https://x.com/adcock_brett/status/1916523850319151225
“you can generate fantastical worlds and “film” them with a fisheye DSLR or retro VHS camera on a FPV drone video generation really does feel like a god mode access to a virtual studio to turn your chaotic dreams into video https://x.com/bilawalsidhu/status/1916637296620679413
IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos
https://y-u-a-n-l-i.github.io/projects/IM-Portrait/
