Digital Life Project 2 (DLP3D)
Watch
Fork
Star
is an open-source real-time framework that brings Large Language Models (LLMs) to life through expressive 3D avatars.
Users converse naturally by voice, while characters respond on demand with unified audio, whole-body animation, and
physics simulation directly in the browser. Characters are fully customizable in both appearance (3D models) and
personality (character prompts) and readily adaptable to any LLM or text-to-speech (TTS) service.
Try it now at dlp3d.ai!
SMPLCap
is a collection of our research projects focusing on advancing (Expressive) Human Pose and Shape Estimation:
- Foundation models:
SMPLest-X,
SMPLer-X,
HMR-Benchmarks
- World-Grounded:
WHAC
- All-in-One-Stage:
AiOS
- Robustness:
RoboSMPLX
- Perspective Distortion:
Zolly
- Point Cloud:
PointHPS
- Alignment:
ADHMR
[2024-04] Outstanding Student Workshop Speaker at China3DV 2024.
[2023-08]
HuMMan is selected for the
PREMIA Best Student Paper Awards.
[2022-04] Selected as Highlighted Reviewer at ICLR 2022.
[2021-09] Selected as Outstanding Reviewer at ICCV 2021.
[2019] Future Star (未来之星) and First batch of AI Pioneers (AI先锋) at SenseTime.
[2019] Lee Kuan Yew Gold Medal (Top 1 in Undergraduate Cohort).
[2019]: Champion of COCO Panoptic Segmentation Challenge at ICCV 2019.
I serve as a reviewer for computer vision, machine learning, robotics conferences/journals
- CVPR, ICCV, ECCV, IJCV
- ICLR, NeurIPS, ICML
- IROS, RA-L