Huan Ling
@HuanLing6
Followers
738
Following
215
Statuses
129
Research Scientist at NVIDIA Toronto AI Lab, research member of Vector Institute. Opinions are my own.
Joined April 2019
RT @zianwang97: 🚀 Introducing DiffusionRenderer, a neural rendering engine powered by video diffusion models. 🎥 Estimates high-quality geo…
0
130
0
RT @karsten_kreis: 🔥 GenMol: Travel through chemical space with an efficient fragment-based representation, modern discrete diffusion, and…
0
17
0
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 downstream applications. More examples at
Cosmos is a developer-first platform designed to help physical AI builders accelerate their development. It has pre-trained world foundation models (diffusion & autoregressive) in different sizes and video tokenizers. They are open models with permissive licenses. Try it out, and let us know how we can better help.
0
18
99
RT @jiawei6_ren: 🔥L4GM code and model weights are finally released! !🔥 Try it and turn your video into a 3D animation in just seconds! Co…
0
21
0
RT @xuanchi13: 📢🚗✨ Excited to announce InfiniCube, our scalable generative model for dynamic 3D driving scene generation with high fidelity…
0
44
0
Checkout our latest 4D reconstrucion paper BTimer! Amazing work from @jiawei6_ren @huangjh_hjh and the team!
Excited to introduce BTimer: a real-time solution for reconstructing dynamic scenes from monocular videos! 🚀 Generate per-frame (bullet-time) 3D GS scenes in 150ms on a single GPU, achieving quality that is on par with the optimization methods! Project:
1
1
19
RT @frncswllms: 📢📢📢 Check out SCube, our new generative model which can reconstruct 100^2m high-resolution photorealistic scenes in <20s gi…
0
29
0
RT @Chenfeng_X: Unfortunately my awesome mentor @orlitany can not come to #CVPR this time. I and @HuanLing6 will present 3DiffTection tomo…
0
2
0
RT @xuanchi13: Our code for XCube is released! Check it out and give it a try! Also come to our poster session #C…
0
5
0
Thank you AK for posting our paper. Project page 😃
L4GM Large 4D Gaussian Reconstruction Model We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview
0
3
15
This week in Seattle, we are going to present our CVPR highlight paper Align your Gaussians but if you are interested in our newly released paper L4GM, come to our Thursday poster session and talk to us!
We present #L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only **seconds**! 1/
0
5
30
RT @amsabour: 📢📢 Align Your Steps: Optimizing Sampling Schedules in Diffusion Models TL;DR: We introduce a method…
0
65
0
@lilianweng Thank you for including videoLDM 😄 I still remember I read your blog in 2021 as the best tutorial to diffusion model 🤣
0
0
12
RT @jonLorraine9: New #NVIDIA #GTC24 paper 🎊 We generate high-quality 3D assets in only 400ms from text by combining (a) amortized optimiz…
0
29
0
RT @jonLorraine9: Or, we could use LATTE3D to initialize text-to-4D methods like Align Your Gaussians: (@HuanLing6,…
0
3
0
@robrombach @pess_r congras Robin! To be honest I feel SD3 should deserve a best paper award somewhere. It's the best diffusion paper I read since imagen paper 😃
1
0
5
Align your Gaussians is accepted by #CVPR2024 . See you in Seattle!
📢📢 Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models We generate dynamic 4D assets and scenes with score distillation! w/ the amazing @HuanLing6*, @seungkim0123*, Antonio Torralba, @FidlerSanja (1/n)
4
8
84