Principal Animation Engineer at NVIDIA. Former Epic Gamer. Enjoy video games, tech, animation, and fun hacks. My tweet is my personal opinion. (she/her)

Joined March 2009
581 Photos and videos
Pinned Tweet
My last talk of #GTC22 on Animation Retargeting is available on VOD if you missed. nvidia.com/en-us/on-demand/s…
8
32
228
Truly groundbreaking work of the team. It's demoed in UE5. #videogame #videogameanimation #robotics #proceduralanimation #nvidia
What is missing to bring real-time motion research into AAA games and real-world robotics? We present MotionBricks, a step toward bridging this gap with two key components: - a single generative latent motion backbone covering 350,000 motion skills, running at 15,000 FPS with 2 ms latency and substantially improved quality and reliability. - a unified smart primitive interface for locomotion, object / scene interaction, with fine-grained control over generated behaviors. Webpage: nvlabs.github.io/motionbrick… Code: github.com/NVlabs/GR00T-Whol… Paper: arxiv.org/abs/2604.24833 (ACM TOG / SIGGRAPH 2026)
1
1
8
567
Lina (혜원) retweeted
Mar 29
soma retargeting for the booster k1!
4
13
78
5,531
Lina (혜원) retweeted
biggest shout out to @SimonYuenNV digital human team and the bones team. Bones dataset laid the foundation of SONIC and Kimodo. it has been my greatest honor and pleasure to be part of this journey! 🫡🫡🫡🔥🔥🔥
Many have asked what dataset we used to train our SOTA motion foundation model Kimodo and SONIC? research.nvidia.com/labs/sil… nvlabs.github.io/GEAR-SONIC/ Bones Studio provides one of the highest quality, large scale humanoid dataset that is ready for AI out of the box. Check it out!
2
1
554
Lina (혜원) retweeted
Many have asked what dataset we used to train our SOTA motion foundation model Kimodo and SONIC? research.nvidia.com/labs/sil… nvlabs.github.io/GEAR-SONIC/ Bones Studio provides one of the highest quality, large scale humanoid dataset that is ready for AI out of the box. Check it out!
Training humanoid robots? You need motion data. Real, high-fidelity, human motion data. And until now - there was no open dataset purpose-built for humanoid robotics. For 5 years, we've been building the largest enterprise-grade human motion and behavior datasets for embodied AI. Our data powered breakthrough SONIC research. Today, at GTC, with @NVIDIARobotics, we're opening a piece of it to the world. BONES-SEED: → 142,200 motion capture animations → Up to 6 natural language descriptions per motion → Temporal segmentation of every action → Curated for humanoid robotics → In NVIDIA SOMA and Unitree G1 (MuJoCo) formats From text to action. Now yours. Go build → bones.studio/datasets/seed #NVIDIAGTC
1
5
19
3,921
Lina (혜원) retweeted
Need high-quality motion for humanoid robots or digital humans? Meet Kimodo: our new diffusion model trained on 700 hours of optical mocap data for easy, controllable, and high-fidelity motion generation. @NVIDIAAI research.nvidia.com/labs/sil…
5
52
209
42,027
Lina (혜원) retweeted
How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k GPU hours and 100M motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: nvlabs.github.io/SONIC/ #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥
8
61
240
61,831
Lina (혜원) retweeted
Thank you, North Carolina. It’s an honor to be your next Attorney General, and I’m ready to get to work.
498
696
15,485
583,753
Lina (혜원) retweeted
🚨 New awesome feature announcement! 🚨 MOTION BLENDING IS HERE! 🚀✨ Blend any motion from our platform - whether it's from video or text - with seamless, AI-driven transitions. From bold moves to subtle shifts, your animations have never looked smoother! #SMPL #3D #Animation #genAI
17
82
572
51,713
Lina (혜원) retweeted
"Best Meta Quest 3 and Quest 3S games 2024" pcgamesn.com/meta/best-quest… Thanks for including NOPE CHALLENGE @PCGamesN!
1
3
245
Lina (혜원) retweeted
The NOPE CHALLENGE "PUMPKIN PATCH" is LIVE! oculus.com/experiences/quest… Update Includes: ✨ UPGRADE TO UNREAL ENGINE 5 🙌 IMPROVED GRABBING AND PHYSICS SYSTEMS 🕷 BUG FIXES 🎃 Enjoy the spooky decorations we've added to get you in the Halloween spirit #Spooky #VR #HappyHalloween
2
6
10
640
Lina (혜원) retweeted
We're running a course on NVIDIA Warp at SIGGRAPH bright and early on Sunday morning 9am-12:15pm, including presentations from @peterchencyc, @pika7ma, @zeshunz, @shinjin_cr, and @c0d1f1ed - hope to see you there!
Discover applications of GPU-accelerated data generation and spatial computing with NVIDIA Warp -- a cutting-edge #Python framework for simulation, #AI, #robotics, and #machinelearning. Join us for hands-on projects with @MIT, @UCLA, and our teams. ➡️ nvda.ws/4bJwHJP See you at #SIGGRAPH2024.
2
15
62
5,968
Lina (혜원) retweeted
2 Jul 2024
Join us for Generative AI Day at #SIGGRAPH2024 to learn about the latest #AI solutions in animation, visual effects, gaming, and more. Stay tuned as we announce exciting #GenerativeAI sessions and register for the conference today. ➡️ nvda.ws/3W8dzR6 📅 July 31
9
20
71
8,306
Lina (혜원) retweeted
My friend Lina (used to work at Epic w her) is throwing this soiree on Thursday at the @RALBeerGarden - if you are an aspiring game cinematic creator or a fan pop in and say hi!
3
15
7,829
Pretty impressive. I tried a couple of videos that are very challenging, but this handled pretty well.
20 Mar 2024
The future of digital humans starts with @meshcapade. At #GDC2024, we've unveiled our updated platform. World's best markerless mocap from a single video. High-quality human motions from text. A new viewer with all the old features. Try it here for free: meshcapade.me
5
461