Scholar
Siyuan Huang
Google Scholar ID: 1NN7Ee8AAAAJ
Beijing Institute for General Artificial Intelligence (BIGAI)
Embodied AI
3D Vision
Robotics
3D Scene Understanding
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
4,740
H-index
37
i10-index
54
Publications
20
Co-authors
17
list available
Contact
Email
huangsiyuan@ucla.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
9 items
Lifting Unlabeled Internet-level Data for 3D Scene Understanding
2026
Cited
0
PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
2026
Cited
0
OmniClone: Engineering a Robust, All-Rounder Whole-Body Humanoid Teleoperation System
2026
Cited
0
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
2026
Cited
0
3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding
2026
Cited
0
OmniTrack: General Motion Tracking via Physics-Consistent Reference
2026
Cited
0
OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
2026
Cited
0
LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
2026
Cited
0
Load more
Resume (English only)
Academic Achievements
SceneWeaver won Best Paper Award at IROS25 RoboGen Workshop (Oct 2025).
UniFP won Best Paper Award at CoRL25, Seoul (Oct 2025).
Selected into the New Generation Star Project at IROS25 (Oct 2025).
First place in IROS25 Robot Dance Competition (Oct 2025); Champion in Solo Dance at the 1st World Humanoid Robot Games (Sep 2024).
Invited keynote speaker at IROS25, CoRL25, CVPR25, and Amazon FAR (2025).
9 papers accepted by CVPR25 and 3 by ICRA25 (Mar 2025).
4 papers accepted by ECCV 2024 (Jul 2024), including SceneVerse, SlotLifter, F-HOI, and PQ3D.
4 papers accepted by CVPR 2024 (Mar 2024), 3 as highlight papers.
Organizing workshops and challenges at CVPR, including the 5th CVPR Workshop on 3D Scene Understanding and the ARNOLD Challenge.
Background
Research Scientist at Beijing Institute for General Artificial Intelligence (BIGAI), directing the Center of Embodied AI and Robotics.
Teaches at Peking University.
Research interests include computer vision, machine learning, cognition, and robotics.
Currently focuses on developing generalizable, language-grounded models for robots to address perception, interaction, learning, and planning.
Long-term goal: build a general-purpose intelligent machine that understands and interacts with the 3D world like humans.
Co-authors
17 total
Yixin Zhu
Assistant Professor, Peking University
Baoxiong Jia
Ph.D. in Computer Science, UCLA
Yixin Chen
University of California, Los Angeles
Tengyu Liu
Beijing Institute for General Artificial Intelligence
Siyuan Qi
Gyges Labs
Xiaojian Ma
University of California, Los Angeles
Ying Nian Wu
UCLA Department of Statistics and Data Science
Qing Li (李庆)
Research Scientist, BIGAI
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up