“Our team is proud to announce Aria Gen 2, the most advanced wearable sensor platform in the world. Following Orion’s announcement last year, and Aria 1st-Gen in 2020, Aria Gen 2 will help us solve challenges on the path to full AR glasses and ContextualAI 😎 https://x.com/TweetEdMiller/status/1895167162244895090
The OS for Human-AI Interaction https://www.tavus.io/
[2503.01661] MUSt3R: Multi-view Network for Stereo 3D Reconstruction https://arxiv.org/abs/2503.01661
“Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it’s pretty neat. These folks basically built a real-time dense SLAM system on top of MASt3R, which is a transformer-based neural network that can do https://x.com/bilawalsidhu/status/1894928469965856854
“We’re closer than ever to a future where we remap the earth 24/7 with a plurality of sensors — phones, drones, cars, planes, satellites, and oh my! This physical 3D model of the world serves as the connective tissue between the world of bits & atoms. It’s Tesla cars today, https://x.com/bilawalsidhu/status/1895288725099421886
InsTaG: Learning Personalized 3D Talking Head from Few-Second Video https://fictionarry.github.io/InsTaG/
“i understand that companies need to make money but don’t pretend you’re doing one thing in your marketing materials when in reality you’re doing a different thing” / X https://x.com/vikhyatk/status/1897964271428080013
“NeRF / 3D scan compilation circa 2022. NVIDIA’s InstantNGP was a particularly nice vintage. First time I could train a radiance field on my gaming pc and watch reality manifest right before my eyes. https://x.com/bilawalsidhu/status/1897107480020443190
“This would be such a zen activity to do in a vr headset — forget bonsai trees, I wanna prune some gaussian splats!” / X https://x.com/bilawalsidhu/status/1895482590162772220
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation https://ltt-o.github.io/Kiss3dgen.github.io/
“Earlier this year, AgiBot open-sourced a large-scale dataset of real-world humanoid robot tasks. Now, they’ve announced AgiBot Digital World, a large-scale simulation framework that includes an open-sourced dataset covering 180+ object categories and 12 core skills. https://x.com/TheHumanoidHub/status/1896616896428126219
“New video up: “LLMs for Creatives In 42 Minutes” Modern LLMs offer creator superpowers far beyond text generation. I’ll walk you through how I built a 3D city simulation, dynamic video annotations, smart shot lists, and even a futuristic HUD overlay using just AI prompts. Plus, https://x.com/bilawalsidhu/status/1897030036684734648
“New dataset from researchers at Meta — uCO3D, or UnCommon Objects in 3D, is the largest publicly-available object-centric dataset for 3D deep learning and 3D generative AI. More on this project ➡️ https://x.com/AIatMeta/status/1898065127859273871
“Highlights of uCO3D: • 170K videos depicting diverse objects from all directions. • Objects spanning ~1000 categories — grouped into 50 super-categories. • Full original videos annotated with object segmentation, camera poses & point clouds. • 3D Gaussian Splat” / X https://x.com/AIatMeta/status/1898065129968918794
“It’s wild to see 3d rendering & interactive experiences slowly being eaten by generative video. Startups Luma and Odyssey have shifted from 3D to AI video to realize their world-building dreams. Research from big labs is even convincing skeptics. 3 must-read papers: 1. https://x.com/bilawalsidhu/status/1896226379617980793
Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture https://xuanchenli.github.io/TexTalk/
