Chen-Hsuan Lin
@chenhsuanlin
Followers
2K
Following
721
Media
24
Statuses
133
Senior research scientist @NvidiaAI • PhD @CMU_robotics • world modeling & 3D content creation 🤖👁🧠🧬
Joined August 2014
Incredibly honored that Neuralangelo has been featured as one of the 🏆 Best Inventions of 2023 by @TIME! I'm really excited to see what Neuralangelo can enable for digital twins, robotics, game dev, and beyond! 🤩.
We’re honored @TIME recognized #NVIDIAResearch's Neuralangleo as one of the 🏆 Best Inventions of 2023. We are excited to see how our community will explore this technology to build 3D renders and scenes. ➡️
3
9
69
RT @hanna_mao: We build Cosmos-Predict2 as a world foundation model for Physical AI builders — fully open and adaptable. Post-train it for….
0
70
0
Cosmos-Predict2 is our latest open video foundation model for Physical AI!. If you’re at #cvpr2025, I would also love to chat with you about world models!.
🚀 Introducing Cosmos-Predict2!. Our most powerful open video foundation model for Physical AI. Cosmos-Predict2 significantly improves upon Predict1 in visual quality, prompt alignment, and motion dynamics—outperforming popular open-source video foundation models. It’s openly
0
5
46
You think camera pose estimation is solved? How about.@nvidia's Racer RTX? We challenge you with ⚡️ Lightspeed benchmark (as part of DynPose-100K release) — crazy wild videos with 𝗴𝗿𝗼𝘂𝗻𝗱-𝘁𝗿𝘂𝘁𝗵 camera poses!. #CVPR2025.
Excited to share ☀️Lightspeed⚡, a photorealistic, synthetic dataset with ground truth pose used for benchmarking alongside DynPose-100K!. Now available for download: Paper accepted to #CVPR2025:
0
12
82
DynPose-100K will be fundamental to building next-generation models that understand and control the 3D visual world. Awesome execution from @_crockwell!.w/ @jt_tung @TsungYiLinCV @liu_mingyu David Fouhey. Paper: Website:
0
0
1
Cameras are key to modeling our dynamic 3D visual world. Can we unlock the 𝘥𝘺𝘯𝘢𝘮𝘪𝘤 3𝘋 𝘐𝘯𝘵𝘦𝘳𝘯𝘦𝘵?! 🌎. 📸 𝗗𝘆𝗻𝗣𝗼𝘀𝗲-𝟭𝟬𝟬𝗞 is our answer! @_crockwell has curated Internet-scale videos with camera pose annotations for you 🤩. Download:
Ever wish YouTube had 3D labels?. 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose!. Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯. Download:
1
10
76
@NVIDIA Cosmos has been recognized as both Best AI and Best overall of #CES2025!! Very honored to be part of the huge team effort. Cosmos will accelerate and shape the future of #PhysicalAI development!.
#NVIDIACosmos world foundation model platform was voted Best #AI and Best Overall at #CES2025. 🎉. Read to see how Cosmos is accelerating #physicalAI development and why it's being recognized for its ability to "enable innovators at CES for years to come." 👇.
0
0
3
Cosmos is also available online -- right in your browser 🤩! Video from Jensen's keynote at CES 2025 🤖:
1
1
5
🌌 NVIDIA Cosmos -- our World Foundation Model platform! Super excited to have made core contributions in multiple aspects. Physical AI is key to modeling the universe of worlds 🌎!. 75-page tech report 📄: Try them out now 😲!
Whether you're a researcher or developer, #NVIDIACosmos world foundation models are now openly available under our permissive license to the physical AI community via NGC & @huggingface. 🤗 #CES2025. See how Cosmos is democratizing #physicalAI development:
2
19
78
RT @DrJimFan: Introducing NVIDIA Cosmos, an open-source, open-weight Video World Model. It's trained on 20M hours of videos and weighs from….
0
749
0
RT @liu_mingyu: Cosmos is a developer-first platform designed to help physical AI builders accelerate their develop….
0
158
0
RT @zhou_xian_: Everything you love about generative models — now powered by real physics!. Announcing the Genesis project — after a 24-mon….
0
3K
0
RT @weichiuma: How to build an AI system that can generate 3D worlds from a single image?. All you need is the **RIGHT** data!. By training….
0
90
0
RT @theworldlabs: We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site….
0
681
0
NVIDIA Edify was announced at SIGGRAPH 2024 earlier in July this year, and Edify 3D is the technology powering the generative 3D API from @Shutterstock. See thread for details:.
Very happy to share the latest release of Edify 3D from NVIDIA, announced at #SIGGRAPH2024!. Edify 3D is the most advanced model for 3D asset generation, trained only on responsible data, and ready for 3D editing!. Try it out on NVIDIA NIM now! 🧵⬇️ (1/5).
0
0
4
We have released a tech report on Edify 3D, documenting our two-year effort at @nvidia on 3D asset generation, from research to product launch!. Paper: Project page: Definitely check out the video with 🔊!.
Creativity unleashed 👨🎨🎨✨ .👀 Edify3D from #NVIDIAResearch explores a new way to generate text-to-#3D images. 📗 Project page: 📝 Paper: . 🔊 sound on
2
19
106
The show was a great team effort from @JiashuXu2 @DonglaiXiang @TsungYiLinCV @FangyinWei @liu_mingyu @zekunhao19951 and many others from NVIDIA!.@SIGGRAPH RTL is by far the most exciting event I have participated in, so be sure to check it out!. (5/5)
0
0
4
We also put on a huge show at #SIGGRAPH2024 Real-time Live!, where we demonstrated how Edify 3D and 360 powers scalable and editable 3D scene generation from only text descriptions!. (4/5).
🏜️ ✨ #NVIDIAResearch used real-time #generativeAI to create an immersive desert world showcasing NVIDIA Edify and the @NVIDIAOmniverse platform. ➡️ 🤠 . Presented at #SIGGRAPH2024 Real-Time Live.
1
0
2
We partner with @GettyImages and @Shutterstock to build responsible visual generative AI services with Edify, trained only on ethically sourced data. See how Edify 3D powers the Generative 3D API from @Shutterstock: ⬇️ (3/5).
1
0
1
NVIDIA Edify is our multimodal architecture for controllable visual content generation. See NVIDIA CEO Jensen Huang's fireside chat at #SIGGRAPH2024 discussing the significance of our Edify foundation models!. ⬇️ (2/5).
1
0
2
Very happy to share the latest release of Edify 3D from NVIDIA, announced at #SIGGRAPH2024!. Edify 3D is the most advanced model for 3D asset generation, trained only on responsible data, and ready for 3D editing!. Try it out on NVIDIA NIM now! 🧵⬇️ (1/5).
1
16
84