Yang (Marino) Li

PhD Student · Rutgers University

Biography

I am a first-year PhD student at Rutgers University - New Brunswick. Fortunate to be advised by Prof. Chengzhi Mao, I am dedicated to bringing 3D Vision to the next stage, empowering it with spatial intelligence through Visual Language Models.

I have been working on Generative AI for 3D Vision, involving generation, inverse rendering, and geometric reconstruction problems. I had wonderful experiences during my internships at LightSpeed Studio Tencent, Microsoft Research Asia, and SmartMore. It has been my honor to collaborate with talented researchers at these institutions, including Yuhan Wang, Jinnan Chen, Jinglu Wang, Xiao Li, Shuai Yang and Jiangbo Lu.

Previously, I received my M.Phil. degree in Artificial Intelligence from HKUST, under the supervision of Prof. Yingcong Chen and Prof. Dan Xu, and obtained my B.S. degree in Mathematics from SYSU.

News

  • • 2025.12: We announced UltraShape 1.0, an open-source Large 3D Shape Generation Model. Technical Report and Code are available on the project page.
  • • 2025.3: I started my research intern at Tencent LIGHTSPEED STUDIOS, working on Large 3D Models. Collaborations are highly welcomed.
  • • 2024.12: I am looking for PhD position in 2025. Please contact me if you are interested.

Experience

  1. Tencent IEG
    Mar 2025 — Present

    Tencent IEG

    Research Intern · LightSpeed Studios Research · Shenzhen, CN

    Working on Large 3D Models for game asset generation.

  2. Microsoft Research Asia
    Jun 2024 — Feb 2025

    Microsoft Research Asia Stars of Tomorrow

    Research Intern · Media Computing Group · Beijing, CN

    Worked on generalizable 3D Gaussian Splatting from unposed videos.

  3. SmartMore
    Jun 2022 — May 2024

    SmartMore

    Research Intern · Optical Imaging Research Group · Shenzhen, CN

    Worked on neural 3D reconstruction with polarization cues.

  4. Sun Yat-sen University
    Mar 2021 — Nov 2021

    Sun Yat-sen University

    Research Assistant · BME AI Lab · Guangzhou, CN

    Worked on biomedical image segmentation.

Publications [Google Scholar]

*: Equal Contribution

: Lattice Attention for Cross-thread Exploration
Arxiv 2026
LACE: Lattice Attention for Cross-thread Exploration
Yang Li, Zirui Zhang, Yang Liu, Chengzhi Mao
Preprint. arXiv:2604.15529. 2026
Paper
: Adaptive Planner Parameter Learning from Vision-Language-Action Model
IROS 2026
APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model
Yuanjie Lu, Beichen Wang, Zhengqi Wu, Yang Li, Xiaomin Lin, Chengzhi Mao, Xuesu Xiao
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2026
Paper
: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
Tech Report
UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
Tanghui Jia, Dongyu Yan, Dehao Hao, Yang Li, Kaiyi Zhang, Xianyi He, Lanjiong Li, Jinnan Chen, Lutao Jiang, Qishen Yin, Long Quan, Ying-Cong Chen, Li Yuan
Preprint. arXiv:2512.21185. 2025
Website Paper Code
ICCV 2025
StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
Yang Li, Jinglu Wang, Lei Chu, Xiao Li, Shiu-hong Kao, Ying-Cong Chen, Yan Lu
International Conference on Computer Vision (ICCV). 2025
Paper
: Multimodal Long Story Generation with Large Language Model
ICCVW 2025 Oral
SEED-Story: Multimodal Long Story Generation with Large Language Model
Shuai Yang, Yuying Ge, Yang Li, Yukang Chen, Yixiao Ge, Ying Shan, Yingcong Chen
Oral, Workshop on Human-Interactive Generation and Editing, International Conference on Computer Vision (ICCV). 2025
Paper Model Data Code
Arxiv 2025
UVRM: A Scalable 3D Reconstruction Model from Unposed Videos
Shiu-hong Kao, Xiao Li, Jinglu Wang, Yang Li, Chi-Keung Tang, Yu-Wing Tai, Yan Lu
Preprint. arXiv:2501.09347. 2025
Paper Demo
: Gaussian guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
ICLR 2024
GNeRP: Gaussian guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
Yang Li, Ruizheng Wu, Jiyong Li, Yingcong Chen
International Conference on Learning Representations (ICLR). 2024
Project Page Paper Data Code
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation
AAAI 2024
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation
Jiyong Li, Dilshod Azizov, Yang Li, Shangsong Liang
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2024
Paper Code
: Densely Connected Deep Convolutional Encoder Decoder Network for Nasopharyngeal Carcinoma Segmentation
Sensors 2021
DCNet: Densely Connected Deep Convolutional Encoder Decoder Network for Nasopharyngeal Carcinoma Segmentation
Yang Li, Guanghui Han, Xiujian Liu
Sensors 2021, 21(23), 7877. 2021
Paper Code

Honors & Awards

Ph.D. Fellowship, Department of Computer Science, Rutgers University 2025
Ph.D. Fellowship, Department of Computer Science, Dartmouth College 2025
Stars of Tomorrow (Award of Excellent Intern), Microsoft Research Asia 2025
McGill & Mila Quebec Ph.D. Fellowship, McGill University 2024
Postgraduate Scholarship, HKUST, GZ 2022
Undergraduate Excellent Scholarship, Sun Yat-sen University 2019

Professional Services

Conference Reviewer:

NeurIPS 25', 26'
ICLR 25', 26'
CVPR 25', 26'
AISTATS 25', 26'
ICML 25', 26'

Research Interests

  • Generative 3D Vision
  • Large Language Models for Vision