The recording is available here:

RT @taiyasaki: 📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention. https://t.c…

RT @xieenze_jr: 🔥 SANA 1.5: A linear Diffusion Transformer pushes SOTA in text-to-image generation! Key innovations: • Depth-growth traini…

Proud to be a part of this great work led by @RfLiang and @zianwang97

RT @DinoFuzi: 📢 Our paper CubeDiff has been accepted to ICLR 2025! 🎉🎉🎉 CubeDiff achieves SOTA panorama generation with only minimal archit…

RT @sara_oblak: 🎉 I’m very excited to announce that our paper “ReMatching Dynamic Reconstruction Flow” has been accepted to ICLR 2025! 🎉

RT @ctnzr: DLSS 4 is the biggest DLSS yet: 8X more efficient graphics for 4K 240Hz rendering 15/16 pixels generated by AI A new transfo…

RT @HuanLing6: I am so proud to be part of this big project. Checkout Cosmos models and see how powerful it is to finetune to physical AI d…

RT @huangjh_hjh: Whether you're a researcher or developer, #NVIDIACosmos world foundation models are now openly available under our permiss…

RT @drmapavone: Complementing DreamDrive, I am thrilled to introduce STORM, which enables fast scene reconstruction with a single feed-forw…

RT @DrJimFan: Update: Felix's farewell letter was just published. I read each and every word. Sharing here with my big audience because it…

RT @DrJimFan: This is the most gut-wrenching blog I've read, because it's so real and so close to heart. The author is no longer with us. I…

@giffmana Genuinely intrigued, what was the most common mistake? Messing up the order of checks?

@mmbronstein @tunguz Or better yet a Vacheron Constantin

@JiaweiYang118 @ruilong_li @yuewang314 @NVIDIAAI Congrats Jiawei, very well deserved!

RT @jon_barron: Fun paper! This is the second time that a radiance field method has been improved by moving from analytically linearizing a…

We were also interested if Unscented Transform was previously used in NeRF/3DGS literature. Interestingly, @jon_barron @PeterHedman3 et al. investigated it as an alternative to their hexagonal pattern in ZipNeRF. UT yielded slightly better quality, but was also a bit slower :)

RT @zhenjun_zhao: 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting @wilson_over, @janickmartinez, @ashmrz10, Nic…

@PhongStormVN Hi, we plan to release it very soon, but need to go through the internal process.