“Ever wondered how roses grow and wither in your backyard?🌹 Our latest work on generating 4D temporal object intrinsics lets you explore a rose’s entire lifecycle—from birth to death—under any environment light, from any viewpoint, at any moment. Project page:”
https://x.com/gengchen01/status/1869111648721490255
“As expected, a small heads up display is likely coming to the next generation of Ray-Ban Meta glasses. I’d suspect we see this launching in the fall, following Meta Connect 2025. This will be a game changer addition, better enabling use cases for live translation, smart https://x.com/tweetsfromasim/status/1871365377495818479
“Put anything, anywhere. Super excited to show you what we’ve been working on these last weeks. It’s NOW available in Fermat. No LoRAs required.”
https://x.com/fermat_app/status/1870150523686428691
“👓 BEST AI Glasses 2025: The ultimate pair of AI glasses you can confidently wear out! Visit Website Now For Exclusive Early Bird Savings:”
https://x.com/Halliday_Global/status/1871571904194371863
“Zuck’s about to drop Ray Bans with a monocular display and an EMG wristband next year. Augmented reality with the current crop of multimodal LLMs is about to get really interesting.
https://x.com/bilawalsidhu/status/1869981930818580922
“Introducing Nymeria, a dataset for improving egocentric human motion understanding for AR and VR devices from @meta_aria
https://x.com/RealityLabs/status/1870122344599171188
LeviTor: 3D Trajectory Oriented
Image-to-Video Synthesis
https://ppetrichor.github.io/levitor.github.io/
[2410.00425v1] ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
https://arxiv.org/abs/2410.00425v1
“3D AI Revolution Has Begun! Odyssey and a Pixar co-founder just dropped Explorer, a revolutionary 3D world generator that turns any image into an editable 3D world. It’s insane. This changes everything. 10 wild examples:
https://x.com/EHuanglu/status/1869449233788702933
“Introducing DI-PCG: A diffusion-based Image2PCG framework that automates Procedural Content Generation, and our first step towards neural symbolic 3D generation. The demo showcases six object categories and can be extended to support customized PCGs. Links in comments. CC:
https://x.com/yshan2u/status/1869983705412129204
[2412.13193v1] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
https://arxiv.org/abs/2412.13193v1
“SqueezeMe: Efficient Gaussian Avatars for VR TL;DR: Three of these Gaussian Splatting avatars can be run at 72 frames per second. It runs locally on a Meta Quest 3 VR headset. Abstract (excerpt): While previous methods require a desktop GPU for real-time inference of a single
https://x.com/janusch_patas/status/1870004080111927524
Visualizing 6D Mesh Parallelism · main
https://main-horse.github.io/posts/visualizing-6d/
“🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project:
https://x.com/liuziwei7/status/1863965769979285894
Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
https://wzzheng.net/Stag/
New physics sim trains robots 430,000 times faster than reality – Ars Technica
https://arstechnica.com/information-technology/2024/12/new-physics-sim-trains-robots-430000-times-faster-than-reality/
“Excited to announce our new work SAT-HMR 🥳 With a better balance of performance and efficiency, it’s the best real-time 3D multi-person mesh estimation model. Check it out here:
https://x.com/XiaoxuanMa_/status/1870494395822395779
Robot Training
“20+ labs just worked together to open source Genesis – a physics engine with a VLM agent that turns text prompts into interactive 4D worlds Think instant physics-accurate environments, camera paths, and character animations – all from natural language 🤯
https://x.com/bilawalsidhu/status/1869572606455853315
“We’re excited to announce the official release of our Genesis Simulator!”
https://x.com/gan_chuang/status/1869526910771831096
Genesis — Genesis 0.2.0 documentation
https://genesis-world.readthedocs.io/en/latest/
Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
https://wzzheng.net/Driv3R/
World Models
“Today is a big day at @odysseyml. We’re sharing Explorer, our first generative world model. We think world models are the next frontier for AI, enabling wonderful new things. To help shape this, Ed Catmull, the iconic founder of Pixar, is joining our board and investing.”
