| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 05 Nov 2025 12:00:44 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"690b3c6c-8dd1"
expires: Mon, 29 Dec 2025 07:43:39 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 990B:2916CC:884EB3:990B51:69522ED3
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 07:33:39 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210046-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766993620.616608,VS0,VE214
vary: Accept-Encoding
x-fastly-request-id: e851d4da4ffdefd291beb3688393f6e54d11f8c8
content-length: 7294
Wynn - Homepage
🀁 Nan Wang
I build neural rendering and world-model systems at the Beijing Academy of Artificial Intelligence (BAAI), exploring how photorealistic simulation accelerates VR, robotics, and autonomous driving.
I earned my M.Sc. in Computer Science from Tongji University and collaborate closely with teams across research and industry.
Neural Rendering
World Models
3D Vision
- Current Algorithm Engineer · BAAI
- Focus Simulation · Neural rendering · Robotics
News
Research
Representative papers are highlighted.
HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning
Xiaoyun Hu*, Xiaohan Yan*, Nan Wang, Xiaowei Song, Gang Wei, Zhicheng Wang
WACV, 2026
We build a large-scale auto-annotated scene-understanding dataset and a lightweight 3D-LLM that efficiently reasons across modalities.
One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
Zheng Geng, Nan Wang, Shaocong Xu, Chongjie Ye, Bohan Li, Zhaoxi Chen, Sida Peng, Hao Zhao
CoRL, 2025 (Oral)
A generative 3D pipeline crafts rich synthetic assets from a single image, enabling accurate one-shot 6D pose estimation.
Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding
Weiqing Xiao*, Hao Huang*, Chonghao Zhong*, Yujie Lin, Nan Wang, Xiaoxue Chen, Zhaoxi Chen, Saining Zhang, Shuocheng Yang, Pierre Merriaux, Lei Lei, Hao Zhao
arXiv, 2025
SA-Radar generates controllable radar cubes conditioned on waveform parameters, enabling rapid what-if analysis for perception stacks.
ORV: 4D Occupancy-centric Robot Video Generation
Xiuyu Yang*, Bohan Li*, Shaocong Xu, Nan Wang, Chongjie Ye, Zhaoxi Chen, Minghan Qin, Yikang Ding, Xin Jin, Hang Zhao, Hao Zhao
arXiv, 2025
An occupancy-centric world model that forecasts robot videos with precise geometry cues for downstream planning.
PUGS: Zero-shot Physical Understanding with Gaussian Splatting
Yinghao Shuai, Ran Yu, Yuantao Chen, Zijian Jiang, Xiaowei Song, Nan Wang, Jv Zheng, Jianzhu Ma, Meng Yang, Zhicheng Wang, Wenbo Ding, Hao Zhao
ICRA, 2025
Gaussian splatting reconstructions paired with physical priors enable zero-shot predictions of material and dynamics properties.
RE0: Recognize Everything with 3D Zero-shot Open-Vocabulary Instance Segmentation
Xiaohan Yan*, Zijian Jiang*, Yinghao Shuai*, Nan Wang, Xiaowei Song, Wenbo Ji, Ge Wu, Jinyu He, Gang Wei, Zhicheng Wang
ICRA, 2025
A 3D zero-shot segmentation pipeline that fuses geometry and semantics to recognize novel categories without labels.
Semantic-Guided Gaussian Splatting with Deferred Rendering
Nan Wang, Xiaohan Yan, Xiaowei Song, Zhicheng Wang
ICASSP, 2025
Semantic cues from 2D foundation models guide material optimization, yielding expressive deferred rendering for 3DGS.
GreedyAgent: A Simple yet Efficient Approach for Meta-learning from Learning Curves
Jinyu He, Xiaowei Song, Xiaohan Yan, Nan Wang, Yuqi Miao, Zijian Jiang, Fei Chao, Yan Zhang, Shengchuan Zhang, Rongrong Ji
ICIC, 2024 (Oral)
A greedy meta-learner that leverages learning-curve statistics for fast adaptation across tasks.
AttenPoint: Exploring Point Cloud Segmentation through Attention-Based Modules
Xiaohan Yan, Nan Wang, Xiaowei Song, Gang Wei, Zhicheng Wang
PRCV, 2024
Attention modules blending local and global structure deliver data-efficient point cloud segmentation.
Projects
A Real2Sim Pipeline for Robotics Simulation
Xiaomi · 2024-06
3D Gaussian Splatting supplies photoreal rendering while ISAAC Sim handles physics, creating realistic rehearsal spaces for robotics.
LLM Science Exam · Using LLMs to Answer Difficult Science Questions
Kaggle · 2023-10
A silver-medal RAG system that ensembles three DeBERTa variants to reason over curated scientific corpora.
Short Bio
I am an M.Sc. student in Computer Science at the CAD Research Center, Tongji University, focusing on 3D vision, neural rendering, and world models.
Before that, I received my B.Sc. in Computing Science and Technology from the Department of Computer Science and Artificial Intelligence, Southwest Jiaotong University in 2022. I was born in Dengfeng, China—home to Mount Song and a vibrant blend of cultural traditions. A broad STEM foundation, including intensive Biology and Chemistry coursework, shapes how I think about multimodal perception.
Research Interests
My research focuses on 3D vision, including neural rendering, world models, and synthetic environments. I aim to leverage sophisticated 3D assets to construct immersive simulations that accelerate AR/VR systems and robotics. If you see an overlap or would like to collaborate, please reach out!
Current & Past Affiliations
Misc
Music 🎶
- Piano (Grade 10, Shanghai Conservatory of Music)
Sports 🏃♂️
- Basketball
- Badminton
- Swimming
- Flying Disc
Languages 💬
- 中文
- English
- 日本語 (learning)
- Français (learning)