Lei (Ray) Yao retweeted
Could this be the ViT moment for 3D scene understanding? 🚀
We revisit the good old Transformer architecture and apply it to 3D scene understanding with minimal modifications. #Volt ⚡️
Project page: yilmazkadir.github.io/Volt/
Arxiv link: arxiv.org/abs/2604.19609
(1/5)
Lei (Ray) Yao retweeted
Excited to present our #CVPR2026 Highlight paper tttLRM today!
We design a LRM with Test-time Training that supports high-res, long sequence and feedforward/online 3D reconstruction with linear complexity.
📍 ExHall A #39
🕞 6/7, 3:30 PM
🎥 Video: youtu.be/uOlNkq_io4c?si=OAKd…
Lei (Ray) Yao retweeted
📢 Excited to share MoScale, the first next-scale prediction framework for text-to-motion generation!
If you’re attending #CVPR, come visit our poster in Session 3, #199, 11:45 AM. We’d love to discuss ideas and feedback!
Paper and code can also be found at zhiwei-zzz.github.io/MoScale.
🔨 Presenting HAMMER at #CVPR2026 today!
📍 Poster Session 4 · ExHall A · Board #221
MLLMs for intention-driven 3D affordance grounding. Code, weights & data all open.
Keen on 3D scene & object understanding? Come say hi!
🔗 rayyoh.github.io/Hammer
Lei (Ray) Yao retweeted
✨Our 3D vision meets robotics papers list in the era of large models now has 80+ papers and crossed 50 stars and growing🚀
github.com/zubair-irshad/Awe…
Topics include policy learning, VLMs and VLAs, 3D Representations including NeRF, Gaussian Splatting, Simulations and Benchmarks and 3D Pretraining.
Check it out now. Contributions/Feedback welcome.
